© 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. 96142
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     estekak
    -0.54
     متعلقه
    -0.50
    InjectAttribute
    -0.50
     Too
    -0.49
    principalColumn
    -0.47
     EXAMPLE
    -0.47
     desi
    -0.47
    )':
    -0.47
     Baillargeon
    -0.46
     Example
    -0.46
    POSITIVE LOGITS
    ,
    0.65
    HtmlAttribute
    0.65
    NameInMap
    0.61
     ovviamente
    0.61
     defaultstate
    0.61
    StructEnd
    0.59
    interopRequire
    0.56
    hébergement
    0.56
     most
    0.54
    kuuta
    0.54
    Activations Density 0.004%

    No Known Activations