© 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. 14756
    Prev
    Next
    INDEX
    Explanations

    legal, academic, and names

    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
     Judith
    -1.59
    Judith
    -1.34
     Champlain
    -0.72
    vacy
    -0.67
     FormsModule
    -0.60
    각주
    -0.59
     endforeach
    -0.58
    ViewInit
    -0.58
    aspectj
    -0.58
    SharedCtor
    -0.57
    POSITIVE LOGITS
    Say
    0.49
    Depend
    0.49
     autorytatywna
    0.49
    bootstrapcdn
    0.47
     olvid
    0.46
     Lindley
    0.46
     препратки
    0.46
    iners
    0.45
     Schwerpunkt
    0.44
    say
    0.44
    Activations Density 0.010%

    No Known Activations