© 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. 12049
    Prev
    Next
    INDEX
    Explanations

    astro

    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
    tec
    -0.95
    teca
    -0.66
     quæ
    -0.62
    phazard
    -0.60
    __":
    -0.58
    യാ
    -0.56
     Administrativna
    -0.55
    cześ
    -0.53
    Tec
    -0.52
     aDecoder
    -0.52
    POSITIVE LOGITS
    stoj
    0.51
     AUD
    0.49
    SqlSession
    0.48
    expandindo
    0.47
    NameInMap
    0.47
     Homo
    0.46
    jedis
    0.46
    tomy
    0.45
     Cracker
    0.45
    cao
    0.44
    Activations Density 0.108%

    No Known Activations