© 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. 5-CLT-HP
    7. 4651
    Prev
    Next
    INDEX
    Explanations

    software and computing

    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
     ModelExpression
    -0.68
    WithIOException
    -0.65
     &___
    -0.59
    PreferredItem
    -0.57
    __":
    -0.56
    windowFixed
    -0.56
    oneofs
    -0.56
     <>",
    -0.53
    cloudf
    -0.53
    vol
    -0.53
    POSITIVE LOGITS
    MemoryWarning
    0.51
    bootstrapcdn
    0.50
     ausz
    0.46
    AnchorStyles
    0.45
     bParam
    0.45
     càng
    0.45
     useHistory
    0.44
    🟩
    0.43
     daarvoor
    0.43
    checked
    0.42
    Activations Density 0.001%

    No Known Activations