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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93905
    Prev
    Next
    INDEX
    Explanations

    iah

    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
    iah
    -0.81
    hah
    -0.64
    IAH
    -0.64
    ps
    -0.61
    oan
    -0.58
    aah
    -0.57
    y
    -0.57
    otis
    -0.56
     batter
    -0.56
    enite
    -0.56
    POSITIVE LOGITS
    AndEndTag
    0.84
     autorytatywna
    0.83
     utafitiHapana
    0.78
     للاسماء
    0.74
     Chwiliwch
    0.73
     kasarigan
    0.71
     مرئيه
    0.71
    contentLoaded
    0.71
     Shakspeare
    0.69
     Ordovician
    0.67
    Activations Density 0.092%

    No Known Activations