© 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. 14696
    Prev
    Next
    INDEX
    Explanations

    life

    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
    siella
    -0.54
    ENODEV
    -0.53
    inher
    -0.53
     Pneumonia
    -0.52
    DIPSETTING
    -0.52
    TargetException
    -0.51
    chyma
    -0.50
    thma
    -0.49
    Filmographie
    -0.49
    SPR
    -0.48
    POSITIVE LOGITS
    TestingModule
    0.77
    انيف
    0.75
    Демографія
    0.66
    InitVars
    0.55
    IntoConstraints
    0.54
     protoimpl
    0.51
    __;
    0.50
     }{@
    0.49
    rungsseite
    0.49
    ylvan
    0.49
    Activations Density 0.022%

    No Known Activations