© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 9295
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    Inside
    -0.79
    inside
    -0.71
     inside
    -0.71
     Inside
    -0.69
    ViewFeatures
    -0.59
    CodedInputStream
    -0.58
    INSIDE
    -0.57
    <bos>
    -0.54
     insides
    -0.54
     INSIDE
    -0.53
    POSITIVE LOGITS
    .")
    
    0.54
    )':
    0.53
    XmlAccessType
    0.53
    $',
    0.52
    <>());
    0.51
    .}}
    0.49
    CloseOperation
    0.48
     Leite
    0.48
     stadium
    0.48
    rotto
    0.48
    Activations Density 0.018%

    No Known Activations