© 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. 39865
    Prev
    Next
    INDEX
    Explanations

    red

    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
     يتيمه
    -0.70
     linkovi
    -0.70
     démocr
    -0.69
    makeText
    -0.65
    ReusableCell
    -0.63
    tvguidetime
    -0.63
    tinyos
    -0.63
     placés
    -0.61
    DataMember
    -0.59
     normaux
    -0.59
    POSITIVE LOGITS
    dings
    0.47
    сього
    0.46
    jects
    0.45
    sistence
    0.44
    ternut
    0.44
    vaders
    0.43
    ecore
    0.43
    chitis
    0.43
    eze
    0.42
    ưỡi
    0.42
    Activations Density 0.641%

    No Known Activations