© 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. 1-CLT-HP
    7. 13130
    Prev
    Next
    INDEX
    Explanations

    these

    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
    UIControlState
    -0.59
     vectorielles
    -0.54
    enschappelijke
    -0.54
    +#+#
    -0.54
    arques
    -0.53
    nyttet
    -0.53
    wurst
    -0.53
     centaines
    -0.53
     وتسجيلات
    -0.52
     depend
    -0.52
    POSITIVE LOGITS
     restores
    0.62
     glows
    0.62
     recovers
    0.62
     shines
    0.60
     slows
    0.59
     realises
    0.59
     achieves
    0.59
     solves
    0.58
     avoids
    0.58
     suppresses
    0.58
    Activations Density 0.007%

    No Known Activations