Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74613
    Prev
    Next
    INDEX
    Explanations

    Fro

    np_max-act-logits · 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
    sizeCache
    -0.98
     дописавши
    -0.78
    Datuak
    -0.71
    MessageOf
    -0.71
    ьаж
    -0.69
    SourceChecksum
    -0.68
     utafitiHapana
    -0.65
    Carriera
    -0.63
    AccessorTable
    -0.63
     betweenstory
    -0.63
    POSITIVE LOGITS
    msgSender
    0.48
    hall
    0.47
    hy
    0.45
    ubic
    0.44
     included
    0.43
    roids
    0.43
     aff
    0.43
    ьа
    0.42
    راض
    0.42
    sub
    0.42
    Activations Density 0.001%

    No Known Activations