© 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. 2-RES-MATRYOSHKA-DC
    7. 7394
    Prev
    Next
    INDEX
    Explanations

    instances of the word "appropriate" or related to appropriateness

    oai_token-act-pair · gpt-4.1-nano
    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
     ideal
    -0.74
     idéale
    -0.71
     Ideal
    -0.70
    levan
    -0.70
     IDEAL
    -0.69
    ideal
    -0.68
    Ideal
    -0.67
     relevance
    -0.66
    relevant
    -0.65
     Relevance
    -0.63
    POSITIVE LOGITS
     Appropriate
    1.52
    Appropriate
    1.52
     appropriate
    1.51
    appropriate
    1.49
     APPROPRI
    1.41
     appropri
    1.26
     appropriateness
    1.25
     inappropriate
    1.23
     inappropri
    1.11
    Inappropriate
    1.09
    Activations Density 0.010%

    No Known Activations