© 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. 45309
    Prev
    Next
    INDEX
    Explanations

    official matters or visiting

    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
    bred
    -0.60
     han
    -0.57
     a
    -0.50
    ika
    -0.50
    нин
    -0.50
    ishan
    -0.50
     مج
    -0.50
    ciano
    -0.49
     After
    -0.47
    bel
    -0.47
    POSITIVE LOGITS
     myſelf
    1.37
     itſelf
    1.32
     Efq
    1.16
    DockStyle
    1.14
     whoſe
    1.13
     auffi
    1.12
     himſelf
    1.11
     Monfieur
    1.11
     ſtate
    1.10
     becauſe
    1.09
    Activations Density 0.289%

    No Known Activations