© 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. 1-CLT-HP
    7. 45577
    Prev
    Next
    INDEX
    Explanations

    ble

    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
     olduğu
    -0.50
    bindParam
    -0.46
    }^{(\
    -0.44
     Wings
    -0.44
     fiind
    -0.43
     című
    -0.43
    insegna
    -0.42
    yorsunuz
    -0.41
    Cited
    -0.41
    AxisAlignment
    -0.41
    POSITIVE LOGITS
    saraba
    0.75
    NameInMap
    0.69
    ptonshire
    0.67
    Parcelize
    0.66
    theless
    0.64
     kasarigan
    0.64
     iſt
    0.61
    IonicModule
    0.61
     lenker
    0.61
    @[+][
    0.60
    Activations Density 0.038%

    No Known Activations