© 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. 20-CLT-HP
    7. 74619
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    middels
    -0.66
     SIMBAD
    -0.49
    FileVersion
    -0.48
    SWR
    -0.47
    pides
    -0.47
     <<<<<<<<<<<<<<
    -0.47
    ituary
    -0.46
    zwischen
    -0.46
     trase
    -0.45
    TextHelper
    -0.45
    POSITIVE LOGITS
    djangoproject
    0.54
     favour
    0.53
     favor
    0.53
     favours
    0.52
    freopen
    0.50
    ngt
    0.49
    liferay
    0.49
     Surface
    0.47
    surface
    0.46
    Emerson
    0.46
    Activations Density 0.000%

    No Known Activations