© 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. 7120
    Prev
    Next
    INDEX
    Explanations

    the presence or mention of parameters

    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
    InjectAttribute
    -0.66
    OGND
    -0.63
    neté
    -0.63
    ỡng
    -0.61
    ISMS
    -0.60
    CanBe
    -0.59
    tedly
    -0.58
     Normdatei
    -0.57
    Parcelize
    -0.56
     récents
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.55
     GenerationType
    0.49
    CrossRef
    0.49
     LoggerFactory
    0.49
     مشين
    0.47
    kopf
    0.44
     Heav
    0.43
    govina
    0.43
    abr
    0.43
     Contactez
    0.42
    Activations Density 1.480%

    No Known Activations