© 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. 1-CLT-HP
    7. 13253
    Prev
    Next
    INDEX
    Explanations

    legal and educational documents

    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
     createSlice
    -0.65
     препратки
    -0.61
     متعلقه
    -0.61
     Buss
    -0.60
    脚注の使い方
    -0.59
     Synopsis
    -0.57
     Prid
    -0.57
    addCriterion
    -0.56
     Statt
    -0.56
     PagesJaunes
    -0.55
    POSITIVE LOGITS
    "
    0.53
    #+#
    0.52
    ftagPool
    0.47
    <bos>
    0.45
     JpaRepository
    0.42
    さん
    0.41
     GenerationType
    0.40
     many
    0.38
     quiser
    0.38
     with
    0.37
    Activations Density 0.007%

    No Known Activations