© 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. 4-CLT-HP
    7. 4451
    Prev
    Next
    INDEX
    Explanations

    get

    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
    TagMode
    -0.61
    =\""
    -0.52
    posób
    -0.51
    tagHelperRunner
    -0.51
    onalds
    -0.49
    措
    -0.48
     erw
    -0.46
     parseFrom
    -0.46
    ☚
    -0.45
    ViewFeatures
    -0.45
    POSITIVE LOGITS
     somebody
    0.71
     someone
    0.67
    someone
    0.61
    somebody
    0.57
    Hochspringen
    0.57
     alguém
    0.55
     alguien
    0.54
    OGND
    0.54
     Somebody
    0.53
     qualcuno
    0.53
    Activations Density 0.002%

    No Known Activations