© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91594
    Prev
    Next
    INDEX
    Explanations

    code/data/chemical names

    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
    <bos>
    -0.73
    '
    -0.60
     is
    -0.52
     and
    -0.51
    (
    -0.49
     was
    -0.47
    ’
    -0.46
    ,
    -0.39
    by
    -0.39
    @
    -0.39
    POSITIVE LOGITS
    GEBURTS
    0.98
    KURZBESCHREIBUNG
    0.96
    PerformLayout
    0.92
    abestanden
    0.86
     سكانية
    0.84
    parsedMessage
    0.84
    تقاوى
    0.83
    
    0.83
     AssemblyTitle
    0.83
    .}~\
    0.82
    Activations Density 0.005%

    No Known Activations