© 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. 92064
    Prev
    Next
    INDEX
    Explanations

    lament

    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
     (
    -0.75
     Tom
    -0.74
     M
    -0.74
     and
    -0.71
     na
    -0.71
     hunting
    -0.70
     P
    -0.68
     E
    -0.68
     re
    -0.67
     S
    -0.66
    POSITIVE LOGITS
     itſelf
    1.58
     myſelf
    1.57
     Jefus
    1.50
     Efq
    1.48
     Anſ
    1.47
     Theſe
    1.43
     purpoſe
    1.39
     Majefty
    1.39
     Houſe
    1.38
     poffible
    1.38
    Activations Density 0.241%

    No Known Activations