© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    version

    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
     оригіналу
    -0.55
     NSObject
    -0.51
     Anſ
    -0.50
     Efq
    -0.49
    তথ্যসূত্র
    -0.49
     fhort
    -0.48
    ковник
    -0.48
     neceff
    -0.48
     keg
    -0.47
     poffe
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.59
     Manley
    0.57
    providedIn
    0.53
    HasMaxLength
    0.51
     mécan
    0.51
     menye
    0.48
    Referanser
    0.48
     händ
    0.48
    onViewCreated
    0.47
    HasColumnType
    0.47
    Activations Density 0.005%

    No Known Activations