© 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. 646
    Prev
    Next
    INDEX
    Explanations

    about

    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
     חיצוניים
    -0.65
    ViewFeatures
    -0.62
    ympto
    -0.61
    fjspx
    -0.61
    awtextra
    -0.60
    ^(@)
    -0.59
     beginnetje
    -0.59
     Bescheid
    -0.57
     defaultstate
    -0.56
     &___
    -0.56
    POSITIVE LOGITS
    rítica
    0.50
    mės
    0.49
     feeling
    0.47
    ạn
    0.47
     where
    0.47
    GOAL
    0.46
     which
    0.45
     szóci
    0.45
    GMENT
    0.44
    datagrid
    0.44
    Activations Density 0.004%

    No Known Activations