© 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. 97465
    Prev
    Next
    INDEX
    Explanations

    more

    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
    DoubleQuotes
    -0.65
    setVerticalGroup
    -0.54
     useAppContext
    -0.53
    /**
    -0.51
    AutoField
    -0.50
    OGND
    -0.50
     consultato
    -0.49
     invokingState
    -0.48
    AnchorStyles
    -0.48
     zure
    -0.47
    POSITIVE LOGITS
     than
    0.59
    føring
    0.55
    Rüyada
    0.54
     denn
    0.50
    opportunities
    0.50
     außer
    0.50
    åde
    0.49
     dasarnya
    0.49
     tools
    0.49
    enoord
    0.48
    Activations Density 0.001%

    No Known Activations