© 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. 2-RES-MATRYOSHKA-DC
    7. 6785
    Prev
    Next
    INDEX
    Explanations

    references to the word "it" in various contexts

    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
    GEBURTSDATUM
    -0.81
    Personendaten
    -0.68
     “
    -0.64
     form
    -0.60
    addGap
    -0.59
     pre
    -0.59
    windowFixed
    -0.58
    blitz
    -0.58
    </tfoot>
    -0.53
     thiệu
    -0.52
    POSITIVE LOGITS
     purpoſe
    0.78
     ſche
    0.77
     Majefty
    0.77
     greateſt
    0.72
     unſ
    0.71
     Houſe
    0.70
     acacia
    0.69
     ſtate
    0.69
     tourmaline
    0.69
     ejus
    0.68
    Activations Density 0.193%

    No Known Activations