© 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. 2273
    Prev
    Next
    INDEX
    Explanations

    the preposition "in", sometimes paired with "an" or "some"

    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
     green
    -0.58
    joins
    -0.58
     join
    -0.56
     Hivatalos
    -0.56
     Inclusion
    -0.56
    occo
    -0.55
    Inclusion
    -0.55
     Green
    -0.54
    join
    -0.54
    clu
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.72
    ineno
    0.68
     onderhoud
    0.68
    GEBURTSDATUM
    0.68
    richTextPanel
    0.68
     Normdatei
    0.63
    scriptcase
    0.62
    +:+
    0.60
     beginnetje
    0.60
     endforeach
    0.60
    Activations Density 0.079%

    No Known Activations