© 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. 97575
    Prev
    Next
    INDEX
    Explanations

    settings and configurations

    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
     draft
    -0.66
    draft
    -0.65
    Viitteet
    -0.64
     drafting
    -0.59
    Награды
    -0.59
     present
    -0.57
    crites
    -0.57
    TagHelper
    -0.57
     présent
    -0.56
    present
    -0.55
    POSITIVE LOGITS
    extAlignment
    0.57
    ValueStyle
    0.56
    úrese
    0.54
    getMinutes
    0.54
     tartalomajánló
    0.51
     amet
    0.51
    wikimedia
    0.51
     manqué
    0.51
    SequentialGroup
    0.50
     TextAlign
    0.50
    Activations Density 0.055%

    No Known Activations