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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91943
    Prev
    Next
    INDEX
    Explanations

    in

    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
     in
    -1.90
    in
    -0.76
     в
    -0.76
    ใน
    -0.75
     In
    -0.73
     în
    -0.73
     on
    -0.69
     into
    -0.69
    In
    -0.66
     for
    -0.66
    POSITIVE LOGITS
     Majefty
    1.31
     Monfieur
    1.28
     Jefus
    1.25
     Efq
    1.24
     ſeveral
    1.14
     myſelf
    1.11
     pleaſure
    1.10
     accordance
    1.09
     ſtate
    1.09
     houſe
    1.09
    Activations Density 1.256%

    No Known Activations