© 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. 0-CLT-HP
    7. 91088
    Prev
    Next
    INDEX
    Explanations

    graduated

    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
    Class
    -0.74
     Class
    -0.68
     handle
    -0.57
    CLASS
    -0.56
     CLASS
    -0.54
    /'+
    -0.49
    abello
    -0.47
    ClassName
    -0.47
     hand
    -0.47
     class
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    1.13
     typelib
    0.93
    OGND
    0.87
    клопе
    0.84
    AddTagHelper
    0.82
     Roskov
    0.75
    Geplaatst
    0.74
    Espèce
    0.73
     Chwiliwch
    0.73
    <bos>
    0.72
    Activations Density 0.044%

    No Known Activations