© 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. 6470
    Prev
    Next
    INDEX
    Explanations

    phrases related to political criticism

    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
    50
    +0.15
    0.7%
    856
    +0.10
    0.4%
    438
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.15
    0.13
    1013
    +0.10
    0.11
    86
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.46
    addComponent
    -0.80
    protected
    -0.79
    public
    -0.75
    //
    -0.75
    <!--
    -0.74
    const
    -0.74
    private
    -0.73
    </thead>
    -0.73
    ัติ
    -0.72
    POSITIVE LOGITS
     disreg
    1.77
     maneu
    1.71
     reluct
    1.69
     Confu
    1.64
     impra
    1.61
     shenan
    1.59
     increa
    1.55
     strick
    1.54
     disagre
    1.54
     apprehen
    1.53
    Activations Density 1.694%

    No Known Activations