© 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. 45112
    Prev
    Next
    INDEX
    Explanations

    heme

    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
    -0.52
     it
    -0.52
     To
    -0.49
    ]^{-
    -0.48
     Christ
    -0.47
    getAs
    -0.47
     her
    -0.46
    EditorBrowsable
    -0.45
     their
    -0.45
     j
    -0.42
    POSITIVE LOGITS
     myſelf
    1.06
     purpoſe
    1.02
     Efq
    1.01
     itſelf
    1.00
     Diſ
    0.95
     poffible
    0.94
     ſever
    0.94
     cauſe
    0.92
     Houſe
    0.92
     pleaſure
    0.92
    Activations Density 1.113%

    No Known Activations