© 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. 72091
    Prev
    Next
    INDEX
    Explanations

    Random snippets

    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
    enumi
    -0.56
     CascadeType
    -0.56
     aneurysm
    -0.54
     Multiple
    -0.54
    caloosa
    -0.54
    owol
    -0.53
     randint
    -0.53
    ButterKnife
    -0.52
    physician
    -0.51
     postIndex
    -0.50
    POSITIVE LOGITS
    proper
    0.64
     proper
    0.63
     loads
    0.58
    0.53
    Proper
    0.52
     Proper
    0.51
     vero
    0.50
    uitable
    0.48
    Stack
    0.47
    mese
    0.47
    Activations Density 0.000%

    No Known Activations