© 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. 42216
    Prev
    Next
    INDEX
    Explanations

    talked

    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
    er
    -0.70
    ered
    -0.68
     étoient
    -0.62
     autorité
    -0.62
     lab
    -0.61
     icône
    -0.61
    lably
    -0.61
    shaft
    -0.59
     everyone
    -0.59
     Integration
    -0.58
    POSITIVE LOGITS
    ंदीखरीदारी
    0.52
     <=",
    0.52
    ization
    0.52
    makeText
    0.52
     smtplib
    0.49
    DebuggerNonUser
    0.48
     night
    0.47
    *>(
    0.46
     alternatively
    0.46
    yarnpkg
    0.46
    Activations Density 0.041%

    No Known Activations