© 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. 1658
    Prev
    Next
    INDEX
    Explanations

    the prefix "inter" followed by a word related to people being part of a group, company, or other organization

    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
     Lightboxes
    -0.70
    ActionCreators
    -0.63
     LUMP
    -0.63
    ugd
    -0.62
    ngrx
    -0.62
     Caso
    -0.58
    kuat
    -0.58
     Mommy
    -0.57
    ToFit
    -0.57
     Cristiano
    -0.56
    POSITIVE LOGITS
     inter
    3.30
     Inter
    3.16
    Inter
    3.09
    inter
    2.91
     INTER
    2.78
    INTER
    2.69
     Inters
    2.03
    Inters
    1.93
    inters
    1.71
     Interv
    1.69
    Activations Density 0.516%

    No Known Activations