© 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. 20-CLT-HP
    7. 77541
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    np_max-act-logits · 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
    principalTable
    -0.72
    ionario
    -0.68
     resourceCulture
    -0.67
     getItemId
    -0.67
    Turning
    -0.66
    Portály
    -0.65
     Himo
    -0.64
     Commentaires
    -0.64
    makeConstraints
    -0.63
     Turning
    -0.62
    POSITIVE LOGITS
     ag
    0.49
    tonode
    0.48
    XmlAccessType
    0.45
    cestors
    0.41
     alarm
    0.41
    RequiresApi
    0.39
    meye
    0.39
    ierzch
    0.38
     wake
    0.38
     saites
    0.37
    Activations Density 0.000%

    No Known Activations