© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 162
    Prev
    Next
    INDEX
    Explanations

    words related to online security measures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.08
    0.3%
    437
    +0.06
    0.2%
    325
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.08
    0.05
    325
    +0.06
    0.05
    284
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.30
     reinstate
    -0.89
     abolish
    -0.85
     rehabilitate
    -0.76
     inaugurate
    -0.76
    /**
    -0.74
     plundered
    -0.73
     endow
    -0.73
     defray
    -0.71
     enshr
    -0.71
    POSITIVE LOGITS
     Secure
    1.50
     secure
    1.43
    Secure
    1.42
    secure
    1.41
     bandung
    1.21
     security
    1.20
     cæ
    1.09
     napoli
    1.08
     jaya
    1.07
     securely
    1.04
    Activations Density 0.124%

    No Known Activations