© 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. 40024
    Prev
    Next
    INDEX
    Explanations

    to

    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
     in
    -0.63
     of
    -0.61
     and
    -0.59
     for
    -0.57
    .
    -0.55
     is
    -0.53
     (
    -0.52
      
    -0.52
     or
    -0.50
    POSITIVE LOGITS
     purpoſe
    1.27
     Diſ
    1.25
     myſelf
    1.23
     itſelf
    1.23
     reaſon
    1.18
     Reſ
    1.16
    ſelves
    1.16
     Houſe
    1.16
     ſmall
    1.16
     Anſ
    1.13
    Activations Density 0.150%

    No Known Activations