© 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. 1-RES-MATRYOSHKA-DC
    7. 286
    Prev
    Next
    INDEX
    Explanations

    expressions of possession

    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
     Normdatei
    -0.82
    AndEndTag
    -0.75
    mektedir
    -0.74
    melidir
    -0.65
    culosis
    -0.65
    ikkert
    -0.65
    Fordítás
    -0.65
    BufferException
    -0.63
    nthesis
    -0.63
     заключа
    -0.62
    POSITIVE LOGITS
    ve
    1.41
    s
    1.34
    re
    1.23
    ll
    1.22
     theyre
    0.95
    d
    0.93
    t
    0.91
    m
    0.85
     youre
    0.82
    Theres
    0.79
    Activations Density 0.689%

    No Known Activations