© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "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
     abbiano
    -0.42
     mitään
    -0.42
    受到了
    -0.42
    日は
    -0.41
     esquecer
    -0.40
    seamnă
    -0.40
    其中的
    -0.40
     con
    -0.40
    wok
    -0.39
    それで
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.93
    enumi
    0.80
     getItemId
    0.77
    enumii
    0.76
     doInBackground
    0.75
     ब्रेकडाउन
    0.73
     المعيارى
    0.73
    PyTuple
    0.73
     kasarigan
    0.72
    脚注の使い方
    0.72
    Activations Density 0.117%

    No Known Activations