© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40273
    Prev
    Next
    INDEX
    Explanations

    Hoo

    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
     Ward
    -0.69
    tagHelperRunner
    -0.66
    oa̍t
    -0.59
    الإنجليزية
    -0.58
     JAXBElement
    -0.57
    IBOutlet
    -0.56
    Ссылки
    -0.55
     Knud
    -0.54
    équipement
    -0.54
    Ward
    -0.52
    POSITIVE LOGITS
    thood
    0.50
    <bos>
    0.47
    ellido
    0.46
    OCCURRED
    0.46
    исленность
    0.46
    dles
    0.46
    hers
    0.45
    teens
    0.44
    bows
    0.42
    standers
    0.41
    Activations Density 0.025%

    No Known Activations