© 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. 254
    Prev
    Next
    INDEX
    Explanations

    questions related to specific inquiry or clarification

    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
     E
    -0.57
     B
    -0.55
    олові
    -0.54
     I
    -0.52
     S
    -0.48
     A
    -0.48
     F
    -0.47
    est
    -0.47
     Hens
    -0.46
     M
    -0.45
    POSITIVE LOGITS
    Q
    3.63
     Q
    3.56
     q
    2.89
    q
    2.73
    Ｑ
    2.30
    Qs
    2.20
    𝑄
    1.67
    ｑ
    1.66
     qs
    1.65
     QQ
    1.65
    Activations Density 1.527%

    No Known Activations