© 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. 1-CLT-HP
    7. 14579
    Prev
    Next
    INDEX
    Explanations

    royal fortifications

    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
    Tembelea
    -0.60
    windowFixed
    -0.59
    igshid
    -0.59
    EndGlobalSection
    -0.56
    :+:
    -0.56
     nonatomic
    -0.56
     Sarg
    -0.55
    Jegyzetek
    -0.53
    ГЛА
    -0.52
    álu
    -0.50
    POSITIVE LOGITS
     she
    0.50
    mtrl
    0.48
     Abbey
    0.48
    attente
    0.47
     cré
    0.45
     سكانية
    0.44
     process
    0.43
    UrlResolution
    0.43
    illo
    0.42
     Vue
    0.42
    Activations Density 0.011%

    No Known Activations