© 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. 45572
    Prev
    Next
    INDEX
    Explanations

    poison/toxicity

    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
     doInBackground
    -0.59
    andoah
    -0.56
    sho
    -0.56
     Signalez
    -0.56
    uarts
    -0.52
    }}$\\
    -0.51
    اعمال
    -0.51
    expandindo
    -0.50
     Paglinawan
    -0.49
    rouvez
    -0.49
    POSITIVE LOGITS
     nakalista
    0.62
     Huns
    0.53
     chal
    0.50
    lnie
    0.49
    GeoNames
    0.48
    ticulture
    0.47
    </thead>
    0.47
    Still
    0.46
    RetentionPolicy
    0.45
     Chal
    0.44
    Activations Density 0.002%

    No Known Activations