© 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. 3519
    Prev
    Next
    INDEX
    Explanations

    browser

    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
    hematical
    -0.54
    bigliamento
    -0.54
    __(/*!
    -0.52
    reibe
    -0.52
     typelib
    -0.52
    GenerationType
    -0.50
    راسیون
    -0.50
    sprozess
    -0.49
     Brill
    -0.49
    POSITIVE LOGITS
    less
    0.57
     ujednoznacz
    0.54
    cap
    0.54
    AnimationsModule
    0.54
     extension
    0.53
    side
    0.52
     taban
    0.52
     agnostic
    0.50
    agnos
    0.50
    based
    0.50
    Activations Density 0.003%

    No Known Activations