© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40105
    Prev
    Next
    INDEX
    Explanations

    work

    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
     Desk
    -0.78
     desk
    -0.75
     genoux
    -0.63
    Desk
    -0.61
     Disc
    -0.58
     DESK
    -0.58
     disc
    -0.56
     disk
    -0.56
    Disc
    -0.56
     NgModule
    -0.55
    POSITIVE LOGITS
    less
    0.69
    work
    0.67
    holder
    0.63
    like
    0.60
    ocracy
    0.58
    SharedDtor
    0.58
    works
    0.57
     raiſ
    0.56
     Shaksp
    0.56
    lands
    0.56
    Activations Density 0.061%

    No Known Activations