© 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. 20-CLT-HP
    7. 76673
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    BufferException
    -0.68
    SBATCH
    -0.68
    #+#
    -0.63
     незавершена
    -0.63
    DoubleQuotes
    -0.62
     iconTwitter
    -0.61
    AndEndTag
    -0.61
    GraphicsUnit
    -0.59
    NameInMap
    -0.58
    tvguidetime
    -0.58
    POSITIVE LOGITS
     pObj
    0.57
     friv
    0.50
     frames
    0.44
     Psal
    0.43
     galinha
    0.42
    حض
    0.42
    <!--[
    0.42
    ("/:
    0.42
     hjemmeside
    0.41
    Anhalt
    0.41
    Activations Density 0.006%

    No Known Activations