© 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. 5-CLT-HP
    7. 95139
    Prev
    Next
    INDEX
    Explanations

    Official announcements

    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
     Minister
    -0.56
     ministries
    -0.54
    mybatisplus
    -0.54
     Ministry
    -0.51
    lappe
    -0.50
     ministry
    -0.50
     ministers
    -0.50
     patties
    -0.49
     eigenvectors
    -0.49
     minister
    -0.48
    POSITIVE LOGITS
     MainAxisSize
    0.82
     stället
    0.71
    曖昧さ回避
    0.67
     mêmes
    0.65
     larmes
    0.64
     enfans
    0.63
     fumée
    0.62
     guerres
    0.62
    skat
    0.60
     lèvres
    0.60
    Activations Density 0.004%

    No Known Activations