© 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. 432
    Prev
    Next
    INDEX
    Explanations

    instances where someone is making a claim which requires supporting evidence

    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
    ides
    -0.64
    ValueStyle
    -0.64
     Catto
    -0.63
     McNamara
    -0.59
    IDO
    -0.58
    WithFormat
    -0.57
    edes
    -0.56
    ido
    -0.54
    IntegerField
    -0.54
    geset
    -0.54
    POSITIVE LOGITS
    Such
    1.62
     such
    1.56
    such
    1.56
     SUCH
    1.55
     Such
    1.51
     solcher
    1.25
     solchen
    1.14
     solche
    1.11
     suche
    1.09
     Такие
    1.07
    Activations Density 0.526%

    No Known Activations