© 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. 3431
    Prev
    Next
    INDEX
    Explanations

    ration

    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
     noastră
    -0.84
    ("]");
    -0.66
     betweenstory
    -0.65
    tonode
    -0.64
     stället
    -0.61
    󠁢
    -0.60
     financeira
    -0.60
     noastre
    -0.60
     nostru
    -0.59
    endroit
    -0.58
    POSITIVE LOGITS
    isy
    0.58
    허
    0.50
     ad
    0.47
    typeorm
    0.45
    Atsauces
    0.44
    容
    0.44
    MT
    0.43
    SY
    0.43
     Vincent
    0.42
     שוליים
    0.42
    Activations Density 0.001%

    No Known Activations