© 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. 4-CLT-HP
    7. 4508
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
    ();)
    -0.59
     Betracht
    -0.56
     Vordergrund
    -0.54
     pass
    -0.54
     facing
    -0.52
    <eos>
    -0.49
     default
    -0.49
    الإنجليزية
    -0.49
     mahdol
    -0.48
     
    -0.48
    POSITIVE LOGITS
    WebElementEntity
    0.65
    another
    0.60
    Another
    0.60
    ftagPool
    0.57
     otro
    0.55
     محفوظة
    0.54
    +#+#
    0.54
    Alternatively
    0.53
     فريبيس
    0.52
    Otro
    0.52
    Activations Density 0.003%

    No Known Activations