© 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. 3-RES-MATRYOSHKA-DC
    7. 2690
    Prev
    Next
    INDEX
    Explanations

    code that has been automatically generated

    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
    ArgsConstructor
    -0.56
    IsContent
    -0.56
    idyl
    -0.54
     rospy
    -0.53
    gheny
    -0.53
    phite
    -0.52
    maked
    -0.52
    chequer
    -0.52
    LEGGI
    -0.52
    =""/>
    -0.52
    POSITIVE LOGITS
     Generated
    1.88
     generated
    1.79
    Generated
    1.63
    generated
    1.58
     created
    1.27
     produced
    1.20
    created
    1.20
     Created
    1.16
    produced
    1.11
    Created
    1.10
    Activations Density 0.027%

    No Known Activations