© 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. 0-RES-MATRYOSHKA-DC
    7. 12180
    Prev
    Next
    INDEX
    Explanations

    references to cutting, trimming, or reducing something

    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
    nage
    -0.59
    doubleValue
    -0.52
    OCO
    -0.51
     Igu
    -0.51
    buster
    -0.50
     hunter
    -0.50
     Pfund
    -0.50
     sledge
    -0.49
    Santiago
    -0.48
     refreshToken
    -0.48
    POSITIVE LOGITS
    cut
    0.93
    CUT
    0.85
     defamation
    0.81
     TestBed
    0.78
     <>",
    0.73
     doInBackground
    0.69
    GraphicsUnit
    0.68
    amation
    0.68
    UnusedPrivate
    0.67
    PropertyChanging
    0.66
    Activations Density 0.059%

    No Known Activations