© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40066
    Prev
    Next
    INDEX
    Explanations

    horizontal

    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
    ing
    -0.86
     horizontal
    -0.77
    lgari
    -0.74
     McQu
    -0.74
    principalTable
    -0.72
    posedge
    -0.71
    ConstraintMaker
    -0.71
    fjspx
    -0.71
    ING
    -0.70
    saraba
    -0.70
    POSITIVE LOGITS
     Coch
    0.49
    VersionUID
    0.45
    Azur
    0.44
     Broome
    0.44
     migrator
    0.42
     coa
    0.42
    $
    0.42
     latter
    0.41
    Abit
    0.41
     tails
    0.41
    Activations Density 0.175%

    No Known Activations