© 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. 0-CLT-HP
    7. 43401
    Prev
    Next
    INDEX
    Explanations

    Opinions and plans

    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
     ↓,
    -0.59
    ColumnHeaders
    -0.58
     Desta
    -0.57
     Wider
    -0.56
     }],
    -0.56
     ulti
    -0.55
     Senti
    -0.55
    ibouti
    -0.55
    styleType
    -0.54
     Baillargeon
    -0.54
    POSITIVE LOGITS
    ting
    0.88
    aneous
    0.74
    ations
    0.73
    ly
    0.73
    ative
    0.73
    ming
    0.73
    ally
    0.72
    ning
    0.71
    tably
    0.69
    ments
    0.68
    Activations Density 0.084%

    No Known Activations