© 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. 6-RES-MATRYOSHKA-DC
    7. 1177
    Prev
    Next
    INDEX
    Explanations

    the word "particular" and sometimes a word appearing near it.

    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
    moons
    -0.60
    seits
    -0.59
    galo
    -0.57
    allu
    -0.54
     Uli
    -0.54
    andina
    -0.54
    oubliez
    -0.54
    يش
    -0.53
     возможности
    -0.53
     ioutil
    -0.53
    POSITIVE LOGITS
     particular
    1.42
    particular
    1.34
    Particular
    1.27
     Certain
    1.22
     Particular
    1.22
     certain
    1.20
     specific
    1.17
     PARTICULAR
    1.14
    Certain
    1.13
     bestimmte
    1.13
    Activations Density 0.362%

    No Known Activations