© 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. 93129
    Prev
    Next
    INDEX
    Explanations

    ito

    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
     विश्वसनीयता
    -0.67
    DECREF
    -0.56
    /**
    -0.55
    mbda
    -0.54
     comigo
    -0.52
    ValueStyle
    -0.52
     препратки
    -0.51
    สึก
    -0.49
     PyTuple
    -0.48
    ưỡi
    -0.48
    POSITIVE LOGITS
     дописавши
    0.59
    PerformLayout
    0.52
    oa̍t
    0.50
    ỡng
    0.49
     ModelExpression
    0.49
    énario
    0.49
    SourceChecksum
    0.48
    EndGlobalSection
    0.48
    SequentialGroup
    0.47
     manda
    0.46
    Activations Density 0.001%

    No Known Activations