© 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. 1-CLT-HP
    7. 418
    Prev
    Next
    INDEX
    Explanations

    process

    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
     CreateTagHelper
    -0.71
    twimg
    -0.64
     gawas
    -0.63
    хьтан
    -0.60
     transfieras
    -0.57
     typelib
    -0.57
     kasarigan
    -0.56
    enumi
    -0.55
    UnknownFieldSet
    -0.54
    rxjs
    -0.52
    POSITIVE LOGITS
    ularia
    0.49
    PARTY
    0.47
    Occasion
    0.46
     regime
    0.46
     defStyleAttr
    0.46
    PARAMETER
    0.44
    carrier
    0.44
    itulo
    0.44
     });
    0.43
    ملكة
    0.43
    Activations Density 0.016%

    No Known Activations