© 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. 3763
    Prev
    Next
    INDEX
    Explanations

    beams of energy

    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
    ustimmung
    -0.50
     lines
    -0.48
     Lines
    -0.47
    //
    -0.46
    TypedDataSet
    -0.46
    hängen
    -0.45
     expend
    -0.45
     cat
    -0.45
     line
    -0.44
    |')
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.84
    TagMode
    0.83
    forming
    0.76
     invokingState
    0.73
    former
    0.73
    sizeCache
    0.70
    enterOuterAlt
    0.69
    width
    0.66
    :✨
    0.65
     touristes
    0.61
    Activations Density 0.002%

    No Known Activations