© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75421
    Prev
    Next
    INDEX
    Explanations

    asking for or giving help

    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
    contentLoaded
    -0.86
    tagHelperRunner
    -0.85
    Portail
    -0.84
    WriteBarrier
    -0.83
    IntoConstraints
    -0.83
     Roskov
    -0.82
     للمعارف
    -0.82
    TagMode
    -0.80
    tableFuture
    -0.77
     FontWeight
    -0.75
    POSITIVE LOGITS
     really
    0.45
     v
    0.43
     ideal
    0.38
    Initializable
    0.37
    v
    0.35
    really
    0.34
     dimo
    0.34
    đ
    0.34
     apagar
    0.34
     resultar
    0.33
    Activations Density 0.001%

    No Known Activations