© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 145
    Prev
    Next
    INDEX
    Explanations

    passage, movement

    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
    Personendaten
    -0.77
    :✨
    -0.66
    `).
    -0.59
    IsMutable
    -0.59
    >';
    -0.59
    flashdata
    -0.57
    ')")
    -0.57
    >");
    -0.57
     temporarily
    -0.56
    }')
    -0.56
    POSITIVE LOGITS
    toMatchSnapshot
    0.54
    出版年
    0.54
    ItemBackground
    0.51
     kiệm
    0.48
     noqa
    0.48
    anguard
    0.48
    szönöm
    0.47
    zarchiwizowane
    0.45
    elemField
    0.45
    raszam
    0.44
    Activations Density 0.003%

    No Known Activations