© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3451
    Prev
    Next
    INDEX
    Explanations

    decades

    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>
    -0.66
    ORPG
    -0.45
    guro
    -0.44
     pan
    -0.44
    presto
    -0.43
    ERTS
    -0.43
     geo
    -0.42
    gridx
    -0.41
    SOCK
    -0.41
    坐
    -0.40
    POSITIVE LOGITS
     of
    0.89
     originais
    0.65
    Espèce
    0.63
    KURZBESCHREIBUNG
    0.63
     विश्वसनीयता
    0.61
    Manbalar
    0.59
     Legendre
    0.58
     Վերցված
    0.58
    \{\\
    0.58
     Houſe
    0.57
    Activations Density 0.002%

    No Known Activations