© 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. 4-CLT-HP
    7. 45
    Prev
    Next
    INDEX
    Explanations

    the

    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
    łosi
    -0.55
    oforms
    -0.53
     BoxFit
    -0.52
     continúas
    -0.52
    FXMLLoader
    -0.49
    onsors
    -0.49
    sient
    -0.49
     Pupil
    -0.48
     güçlü
    -0.46
     respald
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.70
    findpost
    0.66
     transfieras
    0.61
    ionView
    0.60
     незавершена
    0.60
     onAnimation
    0.57
    انيف
    0.56
    Personensuche
    0.56
    رشف
    0.54
     mapStateToProps
    0.54
    Activations Density 0.004%

    No Known Activations