© 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. 96022
    Prev
    Next
    INDEX
    Explanations

    uff

    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
    ftagPool
    -0.60
    ########.
    -0.59
    __':
    -0.53
    +:+
    -0.52
    ValueGeneration
    -0.51
    InvalidProtocol
    -0.47
     Hauser
    -0.46
    juta
    -0.45
    TextBoxColumn
    -0.45
    ksikon
    -0.45
    POSITIVE LOGITS
     LoggerFactory
    0.60
    ArgsConstructor
    0.55
    Controllo
    0.54
     esternos
    0.54
     ویکی‌پدیای
    0.53
     становника
    0.53
    load
    0.52
    허
    0.51
    \{\\
    0.51
    uously
    0.51
    Activations Density 0.002%

    No Known Activations