© 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. 0-CLT-HP
    7. 93620
    Prev
    Next
    INDEX
    Explanations

    other

    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
    Etimo
    -0.55
    Климат
    -0.48
    ITHUB
    -0.48
    <bos>
    -0.48
     vorbei
    -0.47
     iprot
    -0.46
    eating
    -0.46
     dégustation
    -0.44
    execSQL
    -0.44
    fasta
    -0.44
    POSITIVE LOGITS
    StructEnd
    0.75
    abestanden
    0.69
    WebElementEntity
    0.65
    ύπ
    0.65
     BorderSide
    0.64
    webElement
    0.60
    .*")]
    0.60
    AnchorStyles
    0.60
    atterns
    0.59
     مرئيه
    0.58
    Activations Density 0.068%

    No Known Activations