© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96756
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bar
    -0.65
    closeConnection
    -0.63
    ставляет
    -0.56
    nosaurus
    -0.56
    ameter
    -0.56
     Bar
    -0.55
    щет
    -0.55
    ifrance
    -0.55
    といけない
    -0.55
    IATION
    -0.55
    POSITIVE LOGITS
    providedIn
    0.59
     BoxFit
    0.59
    ProgressHUD
    0.57
     springfox
    0.52
     whoſe
    0.52
     AssemblyTitle
    0.52
    IsContent
    0.52
    ftagPool
    0.52
    ScopeManager
    0.52
    displayquote
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.