© 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. 72700
    Prev
    Next
    INDEX
    Explanations

    Gre/Fre

    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
    DebuggerNonUser
    -0.57
    StructEnd
    -0.47
    İstinadlar
    -0.47
    SequentialGroup
    -0.47
    Referències
    -0.46
     Damascus
    -0.43
    amitié
    -0.41
    cuno
    -0.41
    期刊论文
    -0.41
    apprentissage
    -0.40
    POSITIVE LOGITS
     MainAxisSize
    0.69
    EndGlobalSection
    0.55
    endforeach
    0.55
    ViewImports
    0.53
    ImageContext
    0.52
    inde
    0.51
    Портал
    0.51
    يكب
    0.50
    }{*}{
    0.50
    forName
    0.50
    Activations Density 0.003%

    No Known Activations