© 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. 44074
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    kien
    -0.82
    nologies
    -0.80
    es
    -0.78
    er
    -0.69
    lapia
    -0.65
    ed
    -0.59
    numerusform
    -0.57
     ſche
    -0.56
    таратура
    -0.56
    cing
    -0.55
    POSITIVE LOGITS
    Filmografie
    0.57
    ägg
    0.53
    ptus
    0.48
    DEAL
    0.48
    PerformLayout
    0.47
    rungsseite
    0.47
    OGND
    0.47
    enumii
    0.47
    슷
    0.47
    isional
    0.46
    Activations Density 0.078%

    No Known Activations