© 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. 97569
    Prev
    Next
    INDEX
    Explanations

    pulmonary

    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
     Meksiku
    -0.74
    lay
    -0.69
    <bos>
    -0.63
     Anſ
    -0.60
    doubleValue
    -0.59
     subjective
    -0.57
     wireless
    -0.56
     Humor
    -0.55
     fièvre
    -0.54
     Convergence
    -0.54
    POSITIVE LOGITS
    complexContent
    0.64
    bellar
    0.57
    theless
    0.56
     propOrder
    0.56
    MUM
    0.54
    endmodule
    0.51
    ]")]
    0.51
    >--}}
    0.51
    etheless
    0.50
    EDEFAULT
    0.49
    Activations Density 1.735%

    No Known Activations