© 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. 2-RES-MATRYOSHKA-DC
    7. 4331
    Prev
    Next
    INDEX
    Explanations

    mentions of summary or overview 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
     blij
    -0.49
     sõ
    -0.47
     Ellison
    -0.46
    AMR
    -0.46
    ття
    -0.43
    gulier
    -0.43
    ないので
    -0.42
     attitude
    -0.42
    ないと
    -0.42
    ủi
    -0.41
    POSITIVE LOGITS
     Briefly
    3.33
    Brief
    2.14
     briefly
    2.09
    brief
    1.96
     Brief
    1.68
     brief
    1.62
    BRIEF
    1.47
     brevemente
    1.46
     BRIEF
    1.41
     brie
    1.08
    Activations Density 0.007%

    No Known Activations