© 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. 7671
    Prev
    Next
    INDEX
    Explanations

    expressions of positive confirmation or approval

    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
    Negative Logits
    contentLoaded
    -1.16
     disambiguazione
    -1.14
    NameInMap
    -1.11
     myſelf
    -1.09
     saites
    -1.08
    .";
    -1.05
     bezeichneter
    -1.03
     Efq
    -1.03
    Datuak
    -1.02
    }';
    -1.02
    POSITIVE LOGITS
     
    0.69
     Mar
    0.63
    +
    0.60
    The
    0.59
    C
    0.59
    S
    0.59
    T
    0.59
    ee
    0.59
    R
    0.58
    Mar
    0.58
    Activations Density 0.312%

    No Known Activations