© 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. 42449
    Prev
    Next
    INDEX
    Explanations

    cigarette

    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
    -1.72
     myſelf
    -1.71
     Efq
    -1.68
     itſelf
    -1.55
    ſelves
    -1.55
     Theſe
    -1.55
     Jefus
    -1.52
    ſelf
    -1.51
     ainfi
    -1.51
     Anſ
    -1.50
    POSITIVE LOGITS
     (
    0.93
     
    0.88
    ,
    0.88
    .
    0.83
     or
    0.81
     and
    0.81
    -
    0.74
     is
    0.74
     "
    0.73
    ↵
    0.73
    Activations Density 0.196%

    No Known Activations