© 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. 97677
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
     مرئيه
    -1.09
     picioare
    -0.97
    IntoConstraints
    -0.95
    AutoScaleMode
    -0.94
     étoient
    -0.94
     AssemblyTitle
    -0.89
     AssemblyCulture
    -0.89
     avoient
    -0.88
     feroit
    -0.88
    Hochspringen
    -0.86
    POSITIVE LOGITS
     Pat
    0.53
     di
    0.50
     U
    0.50
     
    0.50
     Po
    0.50
     two
    0.49
     de
    0.49
     a
    0.49
     non
    0.49
     und
    0.48
    Activations Density 0.182%

    No Known Activations