© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11698
    Prev
    Next
    INDEX
    Explanations

    treatment

    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
    abestanden
    -0.85
     متعلقه
    -0.80
    DeleteBehavior
    -0.77
     שוליים
    -0.71
    awaiter
    -0.69
    ImageContext
    -0.69
    ########.
    -0.68
    \{\\
    -0.65
     виправивши
    -0.65
     سكانية
    -0.63
    POSITIVE LOGITS
    ︎
    0.50
     Expenditure
    0.49
    ror
    0.46
    tabol
    0.46
    zawa
    0.46
     Raider
    0.46
     desconocido
    0.45
     commute
    0.45
     Raiders
    0.44
     Indemnity
    0.44
    Activations Density 0.022%

    No Known Activations