© 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. 1138
    Prev
    Next
    INDEX
    Explanations

    Join

    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
     dry
    -1.06
    Dry
    -1.06
     Dry
    -1.02
    dry
    -0.93
     Join
    -0.81
    DRY
    -0.81
    JOIN
    -0.79
    Join
    -0.77
     JOIN
    -0.77
     DRY
    -0.72
    POSITIVE LOGITS
     Monfieur
    0.90
     Efq
    0.81
     myſelf
    0.79
     ſta
    0.77
     purpoſe
    0.77
     ſeveral
    0.76
     Jefus
    0.76
     Theſe
    0.75
     theſe
    0.75
     becauſe
    0.75
    Activations Density 0.068%

    No Known Activations