© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94889
    Prev
    Next
    INDEX
    Explanations

    Shane

    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
    ting
    -0.52
    DOUBLE
    -0.42
     til
    -0.42
     우
    -0.42
    ",&
    -0.41
    button
    -0.41
     drept
    -0.40
     argument
    -0.40
     u
    -0.40
     double
    -0.40
    POSITIVE LOGITS
     myſelf
    0.99
     Efq
    0.94
     raiſ
    0.94
     itſelf
    0.86
     pleaſure
    0.84
     ſtate
    0.82
     Theſe
    0.81
     ſeveral
    0.80
     himſelf
    0.80
     Houſe
    0.80
    Activations Density 0.024%

    No Known Activations