© 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. 5-CLT-HP
    7. 5620
    Prev
    Next
    INDEX
    Explanations

    I

    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
     façons
    -0.49
     circo
    -0.42
    }{*}{
    -0.40
    DaoImpl
    -0.40
    adag
    -0.39
    ально
    -0.38
    közi
    -0.38
     Dun
    -0.37
     kun
    -0.37
     C
    -0.37
    POSITIVE LOGITS
    SequentialGroup
    0.85
    StoryboardSegue
    0.78
     بيها
    0.75
    AnchorStyles
    0.73
    OGND
    0.71
    featureID
    0.71
    BufferException
    0.69
     חיצוניים
    0.69
    aarrggbb
    0.67
     dAtA
    0.66
    Activations Density 0.004%

    No Known Activations