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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43715
    Prev
    Next
    INDEX
    Explanations

    project

    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
     autorytatywna
    -0.84
    aarrggbb
    -0.81
     ویکی‌پدی
    -0.73
    nachron
    -0.72
    esez
    -0.70
     repatriation
    -0.68
    Jeografia
    -0.68
    Project
    -0.68
    ronpa
    -0.67
     jadx
    -0.66
    POSITIVE LOGITS
    s
    0.58
    er
    0.55
    DebuggerNonUser
    0.54
    ing
    0.50
    saraba
    0.50
    ième
    0.49
    ería
    0.47
     Guide
    0.45
    oire
    0.44
    hip
    0.44
    Activations Density 1.293%

    No Known Activations