© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14157
    Prev
    Next
    INDEX
    Explanations

    expressions of praise

    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
     contribution
    -0.56
    Linki
    -0.54
     voulu
    -0.54
    🙁
    -0.53
     Contribution
    -0.52
     CONTRIBUTION
    -0.52
    contribution
    -0.51
    yst
    -0.51
     millón
    -0.50
     resented
    -0.49
    POSITIVE LOGITS
     praise
    3.33
     Praise
    2.80
    praise
    2.61
    Praise
    2.42
     praises
    2.20
     praising
    2.02
     praised
    1.88
     PRA
    1.19
     elog
    1.13
     laud
    0.86
    Activations Density 0.000%

    No Known Activations