© 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. 94986
    Prev
    Next
    INDEX
    Explanations

    approximations

    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
     resourceCulture
    -0.92
    tagHelperRunner
    -0.85
     ―――――
    -0.85
    IUrlHelper
    -0.82
     >=",
    -0.82
     Monfieur
    -0.81
    FieldBuilder
    -0.78
     Forse
    -0.78
     الحره
    -0.77
    principalTable
    -0.77
    POSITIVE LOGITS
    !
    0.61
    ,
    0.57
    !!
    0.56
    </b>
    0.53
    !!!
    0.52
    </h2>
    0.48
    )
    0.47
    </strong>
    0.47
    “
    0.46
     oczywiście
    0.46
    Activations Density 0.055%

    No Known Activations