© 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. 4-CLT-HP
    7. 242
    Prev
    Next
    INDEX
    Explanations

    -

    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
     Exacts
    -0.70
    enance
    -0.68
     дописавши
    -0.59
    WriteTagHelper
    -0.58
    الحياه
    -0.56
     propOrder
    -0.56
    CloseOperation
    -0.55
    setVerticalGroup
    -0.55
     Spas
    -0.54
    AutoField
    -0.54
    POSITIVE LOGITS
    1
    0.62
    7
    0.56
    9
    0.52
    8
    0.49
    AnchorStyles
    0.48
    Референце
    0.48
    2
    0.47
    3
    0.47
    5
    0.46
    XXI
    0.45
    Activations Density 0.017%

    No Known Activations