© 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. 2222
    Prev
    Next
    INDEX
    Explanations

    ate

    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
    osus
    -0.45
    +#+#
    -0.44
     oscu
    -0.44
    ね
    -0.44
     شو
    -0.43
    dar
    -0.43
    ucht
    -0.43
     куль
    -0.42
    ksiä
    -0.42
    映
    -0.42
    POSITIVE LOGITS
     Normdatei
    0.75
    ArgsConstructor
    0.75
    NameInMap
    0.69
     negroes
    0.69
    OGND
    0.68
     Roskov
    0.68
     onAnimation
    0.67
     MainAxisSize
    0.67
     actionPerformed
    0.65
    addCriterion
    0.63
    Activations Density 0.000%

    No Known Activations