© 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. 14440
    Prev
    Next
    INDEX
    Explanations

    directory listings

    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
    oredCriteria
    -0.70
    PreferredItem
    -0.68
    HideFlags
    -0.62
    Aircraft
    -0.61
    AutoScaleMode
    -0.60
    LabelTagHelper
    -0.59
    QMetaType
    -0.58
    WriteHeader
    -0.57
     برانيه
    -0.56
    sizeCache
    -0.56
    POSITIVE LOGITS
    们
    0.56
    dike
    0.49
    ftc
    0.48
     AssemblyCompany
    0.47
     jor
    0.47
    invasion
    0.46
    thumbsup
    0.45
    FTC
    0.45
    ίο
    0.45
     condolence
    0.44
    Activations Density 0.035%

    No Known Activations