© 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. 97600
    Prev
    Next
    INDEX
    Explanations

    into

    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
    -0.54
     PyLong
    -0.49
     into
    -0.48
     of
    -0.48
     is
    -0.48
    .
    -0.46
     Le
    -0.45
    ISupport
    -0.42
     as
    -0.42
    ilever
    -0.41
    POSITIVE LOGITS
     Efq
    1.05
     Majefty
    0.95
     Houſe
    0.92
     houſe
    0.91
     whoſe
    0.91
     fubject
    0.91
     ſeveral
    0.91
     Monfieur
    0.90
     Jefus
    0.88
     Chriftian
    0.88
    Activations Density 0.569%

    No Known Activations