© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 234
    Prev
    Next
    INDEX
    Explanations

    intensifiers

    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
    脚注の使い方
    -0.68
     Chwiliwch
    -0.63
     MainAxisSize
    -0.57
    :+:
    -0.57
     îna
    -0.54
     fairly
    -0.53
     setor
    -0.52
     magát
    -0.51
     kuhusu
    -0.50
     pregă
    -0.50
    POSITIVE LOGITS
     Carried
    0.82
     carried
    0.75
    carried
    0.74
     Carry
    0.61
    migrationBuilder
    0.59
    Ord
    0.52
     carry
    0.52
    cod
    0.52
    oneofs
    0.50
    UDO
    0.50
    Activations Density 0.001%

    No Known Activations