© 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. 20-CLT-HP
    7. 72126
    Prev
    Next
    INDEX
    Explanations

    experimental

    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
    Geplaatst
    -0.80
    SizeF
    -0.65
    antMatchers
    -0.57
    quetas
    -0.56
     JSTOR
    -0.55
    Demografia
    -0.54
    FormsModule
    -0.53
    WritableDatabase
    -0.53
    IMPORTED
    -0.53
    suri
    -0.53
    POSITIVE LOGITS
     off
    0.72
     experimental
    0.69
    experimental
    0.66
     Off
    0.63
     Experimental
    0.62
    Off
    0.60
    Experimental
    0.60
     betweenstory
    0.52
    off
    0.51
    SharedCtor
    0.50
    Activations Density 0.001%

    No Known Activations