© 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. 3-RES-MATRYOSHKA-DC
    7. 3098
    Prev
    Next
    INDEX
    Explanations

    the word "cool" combined with other nouns

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    harusnya
    -0.61
     lämp
    -0.53
     Burnham
    -0.52
    oban
    -0.51
     BRAS
    -0.50
    dox
    -0.49
    niad
    -0.49
     Sind
    -0.49
     Hartford
    -0.49
     indef
    -0.49
    POSITIVE LOGITS
     Cool
    3.09
     cool
    3.08
    Cool
    3.06
    cool
    3.00
     COOL
    2.84
    COOL
    2.64
     cools
    2.50
     coolness
    2.48
     coolest
    2.41
     cooler
    2.31
    Activations Density 0.023%

    No Known Activations