© 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. 96105
    Prev
    Next
    INDEX
    Explanations

    seminoma/seminars

    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
    OGND
    -0.67
     AssemblyProduct
    -0.59
    المشاركات
    -0.59
    Schriften
    -0.57
    GOTREF
    -0.54
    Geplaatst
    -0.52
     transfieras
    -0.52
    ⓧ
    -0.52
     eggplant
    -0.51
     AssemblyTitle
    -0.51
    POSITIVE LOGITS
    oles
    0.70
    OLES
    0.53
    oling
    0.50
    oredCriteria
    0.49
    ole
    0.47
    olat
    0.46
    iferous
    0.46
    arians
    0.46
    olas
    0.46
     CONSERV
    0.46
    Activations Density 0.000%

    No Known Activations