© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 92
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to the name "Kilpa di" or "Kilsey."

    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
    241
    +0.10
    0.3%
    1045
    +0.10
    0.3%
    421
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.05
    1120
    +0.10
    0.04
    690
    +0.09
    0.04
    Negative Logits
     khong
    -0.69
     kani
    -0.68
    Nhan
    -0.67
     forbade
    -0.67
     downvoted
    -0.64
     pama
    -0.61
     Camargo
    -0.60
     annihilated
    -0.60
     hien
    -0.60
     aggravate
    -0.60
    POSITIVE LOGITS
     Kil
    1.95
    Kil
    1.81
     kil
    1.73
     Lac
    1.53
    kil
    1.49
    Lac
    1.41
    KIL
    1.24
     lac
    1.20
    lac
    1.16
     KIL
    1.15
    Activations Density 0.289%

    No Known Activations