© 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. 4-CLT-HP
    7. 2065
    Prev
    Next
    INDEX
    Explanations

    modal verbs

    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
    vably
    -0.75
    Personendaten
    -0.55
    irement
    -0.52
     obfer
    -0.50
    +:+
    -0.50
     considér
    -0.49
    IContainer
    -0.48
    umably
    -0.47
    Становништво
    -0.47
    jsxFileName
    -0.47
    POSITIVE LOGITS
     mean
    1.04
    mean
    0.90
     MEAN
    0.89
     Mean
    0.81
    Mean
    0.80
     lead
    0.78
    lead
    0.66
     meant
    0.65
    MEAN
    0.63
     result
    0.62
    Activations Density 0.004%

    No Known Activations