© 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. 2604
    Prev
    Next
    INDEX
    Explanations

    the word "of" in different contexts, sometimes with additional weighting to words followed by the words "the" and "an".

    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
     дописавши
    -0.52
    specifier
    -0.50
    NonNull
    -0.47
     CreateTagHelper
    -0.47
    makeConstraints
    -0.46
    jspx
    -0.46
    fjspx
    -0.45
     sqlalchemy
    -0.43
     виправивши
    -0.43
     might
    -0.42
    POSITIVE LOGITS
    eabouts
    0.74
    วัติ
    0.73
    ^(@)
    0.70
    ISODE
    0.69
    ătoare
    0.69
    careers
    0.67
    virons
    0.66
    paign
    0.66
    ACIAS
    0.65
    utenant
    0.65
    Activations Density 0.568%

    No Known Activations