© 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. 95311
    Prev
    Next
    INDEX
    Explanations

    program

    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
     program
    -0.78
     quæ
    -0.78
    program
    -0.77
     fubject
    -0.74
    Program
    -0.68
     ſtate
    -0.66
     eorum
    -0.66
     perfons
    -0.66
     ſche
    -0.65
     PROGRAM
    -0.65
    POSITIVE LOGITS
    bootstrapcdn
    0.63
    AndEndTag
    0.63
    mapStateToProps
    0.60
    writeField
    0.60
    FailureListener
    0.57
     saites
    0.55
    genstein
    0.53
    WSGI
    0.53
    AutoField
    0.52
    ंदीखरीदारी
    0.50
    Activations Density 0.133%

    No Known Activations