© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15033
    Prev
    Next
    INDEX
    Explanations

    references to the act of being physically handed or passed 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
    ἶ
    -0.53
    retries
    -0.52
    $_['
    -0.51
    ztő
    -0.51
    tvguidetime
    -0.51
    ::_('
    -0.50
     exploring
    -0.47
    mahl
    -0.47
     explorar
    -0.46
    bellar
    -0.46
    POSITIVE LOGITS
     handed
    3.20
    handed
    2.30
     handing
    2.22
     handover
    1.20
    handedly
    1.15
     entreg
    0.85
     للاسماء
    0.79
     informée
    0.78
     überg
    0.77
    hando
    0.75
    Activations Density 0.001%

    No Known Activations