© 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. 1-CLT-HP
    7. 14685
    Prev
    Next
    INDEX
    Explanations

    dev

    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
     modernist
    -1.05
    ise
    -0.77
    AxisAlignment
    -0.68
    ised
    -0.66
     Modern
    -0.66
    ArgsConstructor
    -0.65
    ized
    -0.64
     '\\;'
    -0.64
    enderror
    -0.62
    ize
    -0.61
    POSITIVE LOGITS
     htmlFor
    0.57
    IndentedString
    0.54
    scribers
    0.53
    tracking
    0.50
     linkovi
    0.49
    RotationOrder
    0.47
    openhague
    0.46
    Демографія
    0.46
    stem
    0.45
     bells
    0.45
    Activations Density 0.081%

    No Known Activations