© 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. 42999
    Prev
    Next
    INDEX
    Explanations

    medical and app development

    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
    harma
    -1.67
    StateToProps
    -0.62
    ARMA
    -0.61
    arma
    -0.58
    schild
    -0.56
    ."</
    -0.54
    )':
    -0.54
     warm
    -0.52
    handleSubmit
    -0.50
     sanded
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.67
    aarrggbb
    0.66
     Италијани
    0.58
    Brainz
    0.57
     referenties
    0.56
    principalTable
    0.54
    ContextHolder
    0.53
    ValueStyle
    0.53
    ErrUnexpectedEOF
    0.52
     rabies
    0.52
    Activations Density 0.268%

    No Known Activations