© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    modal verbs

    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
    <bos>
    -0.60
    طيع
    -0.56
    marginHorizontal
    -0.45
     useSelector
    -0.45
    Carriera
    -0.45
     Tafel
    -0.44
    ش
    -0.44
     appreciate
    -0.44
     شهد
    -0.41
     simply
    -0.41
    POSITIVE LOGITS
    ]]
    0.69
    ⓧ
    0.65
     contextLoads
    0.63
     téléphonique
    0.60
    isContained
    0.59
    جستارهای
    0.59
    `,
    0.57
    ItemLayout
    0.57
    ItemBackground
    0.57
    nemia
    0.57
    Activations Density 0.058%

    No Known Activations