© 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. 907
    Prev
    Next
    INDEX
    Explanations

    programming/technical

    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
    انيف
    -0.67
     ravens
    -0.61
    setVerticalGroup
    -0.61
    esModule
    -0.61
     jScrollPane
    -0.60
    poons
    -0.57
    +:+
    -0.56
     NSCoder
    -0.54
    IsMutable
    -0.54
    anglès
    -0.54
    POSITIVE LOGITS
    structed
    0.58
    stdc
    0.54
    noinspection
    0.53
     géographique
    0.47
    InstanceState
    0.47
    orded
    0.46
    حياته
    0.44
    spath
    0.44
     urbanas
    0.43
    Busch
    0.43
    Activations Density 0.004%

    No Known Activations