© 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. 14996
    Prev
    Next
    INDEX
    Explanations

    factor

    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
     Monfieur
    -0.70
    richTextPanel
    -0.70
     Jefus
    -0.66
     Theſe
    -0.65
     raiſ
    -0.60
     itſelf
    -0.60
    Autoritní
    -0.59
     himſelf
    -0.57
     Efq
    -0.57
     fhort
    -0.57
    POSITIVE LOGITS
     to
    0.89
    ECTOS
    0.59
    DeleteBehavior
    0.55
    BagLayout
    0.54
    ScreenState
    0.54
     tau
    0.53
     SqlDbType
    0.52
    dle
    0.51
    pple
    0.51
    newcommand
    0.50
    Activations Density 0.112%

    No Known Activations