© 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. 20-CLT-HP
    4. 75116
    Prev
    Next
    INDEX
    Explanations

    Technical/website snippets

    np_max-act-logits · 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
     Ordering
    -0.49
    artner
    -0.47
    ernoo
    -0.46
     Muss
    -0.46
    nigh
    -0.44
     Synthe
    -0.43
     Single
    -0.43
     single
    -0.43
    yn
    -0.43
    shank
    -0.43
    POSITIVE LOGITS
    OGND
    0.71
    elemField
    0.70
     sumpay
    0.63
    IndentedString
    0.62
    SourceChecksum
    0.59
     @"/
    0.59
     مرئيه
    0.58
    كتشاف
    0.57
    bootstrapcdn
    0.56
    ⓧ
    0.54
    Activations Density 0.009%

    No Known Activations