© 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. 39880
    Prev
    Next
    INDEX
    Explanations

    formation

    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
     EconPapers
    -0.72
     فريبيس
    -0.60
    MemoryWarning
    -0.58
     AssemblyCulture
    -0.47
     vieilles
    -0.46
     manutenzione
    -0.43
     ně
    -0.43
     sportifs
    -0.43
     bè
    -0.43
     battre
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.64
     initComponents
    0.61
    =$((
    0.59
    uxxxx
    0.58
     resourceCulture
    0.57
     PLWABN
    0.57
     Vapour
    0.56
     vapour
    0.56
    XmlAccessorType
    0.56
    HexString
    0.55
    Activations Density 0.163%

    No Known Activations