© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 995
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     of
    -0.60
     (
    -0.53
     from
    -0.53
     in
    -0.51
     is
    -0.51
     ro
    -0.51
     at
    -0.50
     g
    -0.49
     or
    -0.49
     for
    -0.48
    POSITIVE LOGITS
     itſelf
    1.36
     myſelf
    1.27
     Anſ
    1.24
     Monfieur
    1.19
    ſelf
    1.18
    ſelves
    1.16
     purpoſe
    1.13
     Theſe
    1.13
     poffible
    1.11
     reaſon
    1.10
    Activations Density 0.192%

    No Known Activations