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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2844
    Prev
    Next
    INDEX
    Explanations

    the number 4

    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
     ſtate
    -0.66
     ſte
    -0.64
     reaſon
    -0.63
     triad
    -0.61
     Marten
    -0.61
     Methuen
    -0.60
    ITHUB
    -0.59
     rhyme
    -0.59
     leſs
    -0.59
     fowl
    -0.58
    POSITIVE LOGITS
    mybatisplus
    0.75
    Distribuzione
    0.63
    RTLD
    0.61
    Personensuche
    0.60
    schild
    0.58
    WebElementEntity
    0.57
    </tfoot>
    0.57
    UnusedPrivate
    0.57
     saites
    0.57
    contentLoaded
    0.56
    Activations Density 0.218%

    No Known Activations