© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41365
    Prev
    Next
    INDEX
    Explanations

    agreement/opinions

    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
    TagMode
    -0.92
     createState
    -0.81
    ///</
    -0.79
    ThroughAttribute
    -0.77
    agreed
    -0.68
     Counselor
    -0.68
    saraba
    -0.67
     незавершена
    -0.67
     counselors
    -0.66
     agreed
    -0.65
    POSITIVE LOGITS
    pez
    0.59
    posti
    0.57
    SupportActionBar
    0.56
     mand
    0.56
    ')));
    0.56
     hands
    0.54
     Tans
    0.54
     Shakspeare
    0.54
     commercial
    0.53
     Posi
    0.52
    Activations Density 0.087%

    No Known Activations