© 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. 5-CLT-HP
    7. 93403
    Prev
    Next
    INDEX
    Explanations

    leave

    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
    ждый
    -0.40
    selves
    -0.40
    žni
    -0.38
     doesn
    -0.38
     similares
    -0.37
     reino
    -0.37
    ág
    -0.35
    readLine
    -0.35
    Bigg
    -0.35
    AnchorStyles
    -0.35
    POSITIVE LOGITS
    Personensuche
    0.96
     EconPapers
    0.96
     them
    0.85
     you
    0.73
    WithIOException
    0.71
    BeginInit
    0.70
    WebVitals
    0.69
    OGND
    0.69
    esterday
    0.68
    ValueGenerated
    0.66
    Activations Density 0.003%

    No Known Activations