© 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. 93275
    Prev
    Next
    INDEX
    Explanations

    Jerry

    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
     pleaſure
    -1.01
    Personendaten
    -0.86
     themſelves
    -0.86
     itſelf
    -0.85
     purpoſe
    -0.84
     ―――――
    -0.78
     ſeveral
    -0.78
     leaſt
    -0.77
     himſelf
    -0.77
     nakalista
    -0.77
    POSITIVE LOGITS
     the
    0.62
    avel
    0.57
     I
    0.55
    <eos>
    0.54
    ScopeManager
    0.54
     S
    0.53
    n
    0.53
    ITABLE
    0.52
     Ar
    0.52
     a
    0.51
    Activations Density 0.062%

    No Known Activations