Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12413
    Prev
    Next
    INDEX
    Explanations

    ropy

    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
     Trot
    -0.68
     Telegram
    -0.68
     telegram
    -0.65
    mybatisplus
    -0.63
    rungsseite
    -0.59
     myſelf
    -0.58
     himſelf
    -0.57
     itſelf
    -0.57
     >=",
    -0.56
     becauſe
    -0.55
    POSITIVE LOGITS
    ########.
    0.68
    Билгалдахарш
    0.55
    ver
    0.55
    complexType
    0.52
    TagHelper
    0.52
     hech
    0.52
    styleUrls
    0.51
    helial
    0.50
    sive
    0.50
    vano
    0.49
    Activations Density 0.010%

    No Known Activations