© 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. 0-CLT-HP
    7. 39834
    Prev
    Next
    INDEX
    Explanations

    factors

    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
     factors
    -1.75
    factors
    -1.39
     Factors
    -1.27
     factor
    -1.21
     FACTORS
    -1.17
     facteurs
    -1.13
     Faktoren
    -1.13
     factores
    -1.09
     faktor
    -1.09
    factor
    -1.06
    POSITIVE LOGITS
    SequentialGroup
    0.77
    zzleHttp
    0.77
     AssemblyVersion
    0.73
     newOwner
    0.70
     NSCoder
    0.69
     GoogleFonts
    0.63
    licité
    0.62
     EClass
    0.62
    MLLoader
    0.61
    openzeppelin
    0.60
    Activations Density 0.134%

    No Known Activations