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. 74591
    Prev
    Next
    INDEX
    Explanations

    ap

    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
    Controllo
    -0.59
    makeText
    -0.59
     AssemblyCulture
    -0.57
    ềm
    -0.57
    ukone
    -0.56
    BufferException
    -0.55
    FieldBuilder
    -0.55
    Enllaces
    -0.53
     nonUne
    -0.51
     Référence
    -0.49
    POSITIVE LOGITS
    alsy
    0.65
    alm
    0.61
    alse
    0.59
    alsey
    0.58
    RA
    0.56
    als
    0.53
    lasi
    0.52
     arşivlendi
    0.51
    лас
    0.51
    alsa
    0.50
    Activations Density 0.006%

    No Known Activations