© 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. 4570
    Prev
    Next
    INDEX
    Explanations

    Verb phrases

    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
    lesias
    -0.49
    stawa
    -0.48
    zupeł
    -0.47
     bedo
    -0.47
     köl
    -0.46
    imread
    -0.46
     وسلم
    -0.45
     lenker
    -0.44
    apsed
    -0.43
     obicei
    -0.43
    POSITIVE LOGITS
    ագրություններ
    0.72
     resourceCulture
    0.66
     للاسماء
    0.63
    Билгалдахарш
    0.62
    AxisAlignment
    0.59
    Personendaten
    0.59
    AndEndTag
    0.58
    DispatchToProps
    0.57
    getItemId
    0.56
     Insee
    0.55
    Activations Density 0.004%

    No Known Activations