© 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. 1-RES-MATRYOSHKA-DC
    7. 762
    Prev
    Next
    INDEX
    Explanations

    scientific reports or experimental confirmation statements

    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
    EDEFAULT
    -0.65
     متعلقه
    -0.62
     odkazy
    -0.58
    Interes
    -0.55
    qian
    -0.54
    elementAt
    -0.54
     Margo
    -0.53
     Roskov
    -0.53
    évaluateur
    -0.52
    duction
    -0.51
    POSITIVE LOGITS
     confirmed
    4.06
     confirm
    3.95
     confirmation
    3.77
     confirming
    3.63
     Confirm
    3.61
     confirms
    3.56
    confirmed
    3.52
     Confirmed
    3.52
    confirm
    3.38
     Confirmation
    3.38
    Activations Density 0.495%

    No Known Activations