© 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. 38719
    Prev
    Next
    INDEX
    Explanations

    {

    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
     itſelf
    -1.45
     Monfieur
    -1.34
     Theſe
    -1.30
     Efq
    -1.22
     theſe
    -1.20
     للاسماء
    -1.19
     pleaſure
    -1.18
     ſeveral
    -1.16
     poffible
    -1.13
     myſelf
    -1.12
    POSITIVE LOGITS
     are
    0.90
     (
    0.74
     
    0.74
     A
    0.69
     M
    0.68
     T
    0.67
     d
    0.65
     h
    0.64
     m
    0.62
     r
    0.62
    Activations Density 1.742%

    No Known Activations