© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5579
    Prev
    Next
    INDEX
    Explanations

    code, urls, technical writing

    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
    InstrumentedTest
    -0.63
    Collegamenti
    -0.50
     noten
    -0.46
     <>",
    -0.45
    EndInit
    -0.44
    printStackTrace
    -0.44
     też
    -0.41
    ...
    -0.40
     also
    -0.40
    יסטור
    -0.40
    POSITIVE LOGITS
    CloseOperation
    0.85
     contextLoads
    0.85
     myſelf
    0.72
    ſelf
    0.71
     unſ
    0.69
    TTTT
    0.69
    '},
    0.69
     Eury
    0.69
     simplifié
    0.69
     Houſe
    0.68
    Activations Density 0.018%

    No Known Activations