© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90720
    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
    didSet
    -0.49
     yesterday
    -0.48
    MutableLiveData
    -0.47
     Kette
    -0.47
     along
    -0.46
     casquette
    -0.46
     restauration
    -0.43
     curto
    -0.43
     civile
    -0.43
     parall
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    0.80
    ftagPool
    0.78
    +:+
    0.75
    abestanden
    0.69
    fjspx
    0.69
    HtmlAttribute
    0.67
     unknownFields
    0.67
    Hochspringen
    0.66
    AutoScaleMode
    0.66
    出版年
    0.65
    Activations Density 1.731%

    No Known Activations