© 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. 93897
    Prev
    Next
    INDEX
    Explanations

    area

    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
     inflation
    -0.56
    คาร
    -0.48
     combustion
    -0.47
    TestingModule
    -0.47
     CGSize
    -0.45
     pose
    -0.45
     []:
    -0.44
     suffering
    -0.43
    NgModule
    -0.43
     Inflation
    -0.43
    POSITIVE LOGITS
    <bos>
    0.77
     myſelf
    0.72
     itſelf
    0.71
    saraba
    0.66
    windowFixed
    0.66
    DockStyle
    0.63
    UserScript
    0.63
    équi
    0.62
    berdayakan
    0.60
     Wiktionnaire
    0.60
    Activations Density 0.087%

    No Known Activations