© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    expressions or mentions of interference or the inability to interfere

    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
     estekak
    -0.73
     personalities
    -0.58
    kháu
    -0.58
    iastes
    -0.58
     otomatig
    -0.58
    makeText
    -0.57
    ProgressHUD
    -0.57
    >'+
    -0.56
    PerformLayout
    -0.55
     LCCN
    -0.54
    POSITIVE LOGITS
     interfere
    2.42
     interferes
    1.98
     interfered
    1.72
     interfering
    1.69
     intervene
    0.75
     Efq
    0.71
    ()?;
    0.69
     impede
    0.68
    Cause
    0.68
    endregion
    0.67
    Activations Density 0.002%

    No Known Activations