© 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. 40970
    Prev
    Next
    INDEX
    Explanations

    slim

    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
    IntoConstraints
    -0.81
     Slim
    -0.79
     slim
    -0.75
     MainAxisSize
    -0.74
    ://
    -0.73
     Infórmanos
    -0.73
    RTLD
    -0.71
    Slim
    -0.70
    opold
    -0.69
    miyorum
    -0.65
    POSITIVE LOGITS
    my
    0.50
    mer
    0.48
    tel
    0.43
    ty
    0.41
    cy
    0.41
    }.
    0.41
    tem
    0.41
     delen
    0.40
    me
    0.40
    ww
    0.40
    Activations Density 0.189%

    No Known Activations