© 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. 528
    Prev
    Next
    INDEX
    Explanations

    exclamation points and related formatting

    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
    gdx
    -0.85
    aure
    -0.82
     Rump
    -0.79
     Rés
    -0.79
     AUC
    -0.76
    carter
    -0.74
     Carter
    -0.70
     Zer
    -0.69
    EDE
    -0.69
    "):
    -0.69
    POSITIVE LOGITS
    %!
    1.78
     !
    1.73
    !
    1.70
    ?!?
    1.63
    !"
    1.62
    !!!!!!
    1.58
    !!!!!!!
    1.57
    ?!?!
    1.52
    !”
    1.49
    !!!!!!!!!!
    1.48
    Activations Density 0.283%

    No Known Activations