© 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. 1-CLT-HP
    7. 9586
    Prev
    Next
    INDEX
    Explanations

    conference

    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
     InputDecoration
    -0.54
    tymologie
    -0.51
     conference
    -0.50
     Conference
    -0.47
    SourceChecksum
    -0.46
    foglal
    -0.44
    asantry
    -0.44
     Bishop
    -0.43
    Conference
    -0.43
    ndra
    -0.43
    POSITIVE LOGITS
    windowFixed
    0.70
    ivasan
    0.57
    UnknownFieldSet
    0.56
     transfieras
    0.56
     fieldNum
    0.55
     ostavi
    0.54
    usercontent
    0.54
     Mythology
    0.53
    imageshack
    0.53
     awakeFromNib
    0.52
    Activations Density 0.052%

    No Known Activations