© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78088
    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
    Negative Logits
    __*/
    -0.54
     continuant
    -0.51
    atorze
    -0.50
     void
    -0.47
     đỉnh
    -0.46
    చ్
    -0.45
     لينك
    -0.45
     face
    -0.44
     SqlParameter
    -0.44
    VolleyError
    -0.43
    POSITIVE LOGITS
     transfieras
    0.63
    podar
    0.58
    stateMutability
    0.57
     kaynağından
    0.57
     RSSSF
    0.56
    UnknownFieldSet
    0.56
     Majefty
    0.55
     Jefus
    0.54
    addCriterion
    0.54
     gainera
    0.54
    Activations Density 0.007%

    No Known Activations