© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93151
    Prev
    Next
    INDEX
    Explanations

    fashioned

    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
    fifths
    -0.99
    thirds
    -0.97
    DockStyle
    -0.81
    ResumeLayout
    -0.76
    tichetta
    -0.72
    EndContext
    -0.71
    brainer
    -0.71
     Mad
    -0.69
    oldest
    -0.69
     glisser
    -0.69
    POSITIVE LOGITS
     itſelf
    0.84
    s
    0.82
     Monfieur
    0.77
     myſelf
    0.73
     Reſ
    0.72
     ſeveral
    0.70
     ſever
    0.69
    y
    0.68
     diſt
    0.66
     Anſ
    0.66
    Activations Density 0.104%

    No Known Activations