© 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. 0-CLT-HP
    7. 42685
    Prev
    Next
    INDEX
    Explanations

    }}{{

    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
     Newsom
    -1.13
     allot
    -1.11
     Majefty
    -0.89
    PostInfinity
    -0.79
     itſelf
    -0.76
    InjectAttribute
    -0.75
     Efq
    -0.74
     Theſe
    -0.74
     pleaſure
    -0.74
    NUMX
    -0.73
    POSITIVE LOGITS
    mic
    0.52
    ful
    0.50
    n
    0.49
    rik
    0.48
    িক
    0.48
    mal
    0.47
    ("'"
    0.47
    ěr
    0.46
    mond
    0.45
    co
    0.45
    Activations Density 0.366%

    No Known Activations