© 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. 6068
    Prev
    Next
    INDEX
    Explanations

    references to personal statements or expressions of personal opinion

    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
    anmoins
    -0.68
    cemic
    -0.63
     kuiten
    -0.61
    anoia
    -0.58
     تضيفلها
    -0.58
    rugated
    -0.58
     Toutefois
    -0.57
    ांकि
    -0.56
    Datuak
    -0.56
    ekyll
    -0.56
    POSITIVE LOGITS
    I
    0.85
    OGND
    0.69
     themſelves
    0.65
    ItemBackground
    0.64
    UnsafeEnabled
    0.60
    aarrggbb
    0.60
    Cordialement
    0.60
    regon
    0.59
    évaluateur
    0.59
     their
    0.58
    Activations Density 0.149%

    No Known Activations