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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94976
    Prev
    Next
    INDEX
    Explanations

    idental

    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
     tertutup
    -0.53
     vengo
    -0.51
     travailleurs
    -0.49
     kasarigan
    -0.48
    tainen
    -0.46
    banco
    -0.46
     chaînes
    -0.46
     Behaup
    -0.45
     ouvertes
    -0.45
     terbuka
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.76
    enderror
    0.70
     propTypes
    0.69
    migrationBuilder
    0.69
    createServer
    0.59
    formik
    0.59
    ItemBackground
    0.59
     AsyncTask
    0.57
    neſs
    0.56
    AnchorStyles
    0.55
    Activations Density 0.004%

    No Known Activations