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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 374
    Prev
    Next
    INDEX
    Explanations

    the name "Dan" specifically

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1604
    +0.14
    0.8%
    528
    +0.14
    0.8%
    1573
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.14
    0.03
    1573
    +0.14
    0.02
    1604
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.81
    lateinit
    -0.63
    ContentAlignment
    -0.59
    interface
    -0.59
        
    -0.58
    >>
    -0.58
    Kích
    -0.57
    prime
    -0.57
     o
    -0.57
    |
    -0.56
    POSITIVE LOGITS
     Juf
    1.49
     Dan
    1.37
     disagre
    1.35
     inev
    1.34
     shenan
    1.33
     increa
    1.33
     indestru
    1.31
     maneu
    1.31
     fortn
    1.28
     scrat
    1.28
    Activations Density 0.249%

    No Known Activations