© 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. 92712
    Prev
    Next
    INDEX
    Explanations

    Legal/official bodies

    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
     of
    -0.86
    IndentedString
    -0.75
    committee
    -0.63
    ]--;
    -0.63
    脚注の使い方
    -0.57
    (");
    -0.57
    MLLoader
    -0.56
    ]")]
    -0.54
     committee
    -0.53
     của
    -0.53
    POSITIVE LOGITS
    ImageContext
    0.58
    Bronnen
    0.54
     medulla
    0.54
    ⓧ
    0.49
     Procedural
    0.48
    seamnă
    0.46
    osocial
    0.45
    mogorov
    0.45
     Engraving
    0.44
    urbing
    0.44
    Activations Density 0.047%

    No Known Activations