© 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. 4091
    Prev
    Next
    INDEX
    Explanations

    mentions of residual metal content or residual metal nuclei

    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
     otomatig
    -0.81
    ⓧ
    -0.75
    Nazionale
    -0.69
    WebVitals
    -0.68
    UnsafeEnabled
    -0.68
     jsPsych
    -0.68
    Bibliograf
    -0.67
    Παραπομπές
    -0.66
     Battista
    -0.65
    Datuak
    -0.65
    POSITIVE LOGITS
     residual
    3.05
     Residual
    2.83
    residual
    2.75
    Residual
    2.75
     residuals
    2.55
     resid
    1.45
     RESID
    1.35
    resid
    1.19
    残
    1.19
     residue
    1.16
    Activations Density 0.004%

    No Known Activations