© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95163
    Prev
    Next
    INDEX
    Explanations

    conval

    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
    EDEFAULT
    -0.52
     Waray
    -0.42
    hed
    -0.41
    unction
    -0.41
    NameInMap
    -0.39
    HED
    -0.39
     pien
    -0.39
     trouverez
    -0.39
    waukee
    -0.38
    PositiveButton
    -0.38
    POSITIVE LOGITS
    escent
    0.71
     AssemblyCulture
    0.69
    es
    0.66
    escens
    0.65
    BufferException
    0.64
     SCL
    0.62
    escence
    0.61
     propOrder
    0.61
     Мексичка
    0.60
    StylePriority
    0.60
    Activations Density 0.002%

    No Known Activations