© 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. 0-CLT-HP
    7. 42593
    Prev
    Next
    INDEX
    Explanations

    dissected

    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
     Section
    -0.61
     secular
    -0.60
    Section
    -0.57
    numerusform
    -0.53
    CloseOperation
    -0.49
    richTextPanel
    -0.48
    SequentialGroup
    -0.47
     section
    -0.46
    UrlResolution
    -0.45
     Constitucional
    -0.44
    POSITIVE LOGITS
     endfor
    0.57
    reebok
    0.55
     Refle
    0.54
     />);
    0.54
     Adhe
    0.54
    pidou
    0.53
     Bere
    0.53
    unteering
    0.53
    Portail
    0.51
    coring
    0.51
    Activations Density 1.750%

    No Known Activations