© 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. 41795
    Prev
    Next
    INDEX
    Explanations

    science

    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
    ^(@)
    -1.09
    agascar
    -1.03
    leſs
    -1.02
     myſelf
    -1.02
    esterday
    -1.02
    ipheral
    -1.01
    iffance
    -1.01
     Majefty
    -0.99
    tershire
    -0.98
    gorithm
    -0.97
    POSITIVE LOGITS
    ting
    0.65
    v
    0.64
    ty
    0.63
    no
    0.63
    sh
    0.63
    ms
    0.63
    mi
    0.62
    c
    0.62
    _
    0.60
    rc
    0.60
    Activations Density 0.108%

    No Known Activations