© 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. 1-CLT-HP
    7. 14686
    Prev
    Next
    INDEX
    Explanations

    info

    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
    Info
    -1.96
    info
    -1.96
    INFO
    -1.82
     info
    -1.72
     Info
    -1.66
     INFO
    -1.45
    getInfo
    -1.12
     information
    -1.07
    infos
    -1.07
     infos
    -1.06
    POSITIVE LOGITS
    expandindo
    0.64
    ftagPool
    0.62
    enderror
    0.58
    )))
    0.57
    DeleteBehavior
    0.55
    yntaxException
    0.54
    >");
    0.54
    atisk
    0.54
     Curs
    0.52
     HAP
    0.52
    Activations Density 0.013%

    No Known Activations