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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10847
    Prev
    Next
    INDEX
    Explanations

    click button

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.64
     Motley
    -0.60
     beren
    -0.59
     Kopi
    -0.58
    %");
    -0.56
     bonsai
    -0.56
     Snowy
    -0.56
     enduro
    -0.54
    ]++;
    -0.54
    cetamol
    -0.54
    POSITIVE LOGITS
    帖最后由
    0.60
    <bos>
    0.54
    transQ
    0.53
    oredCriteria
    0.52
    __':
    0.51
     initComponents
    0.51
    ToTable
    0.51
    ArgumentParser
    0.51
    fony
    0.50
    GroupLayout
    0.49
    Activations Density 0.032%

    No Known Activations