© 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. 13250
    Prev
    Next
    INDEX
    Explanations

    references or mentions of charitable giving activities

    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
     Audiodateien
    -0.77
     يتيمه
    -0.66
    JNIEnv
    -0.66
    give
    -0.64
     calitate
    -0.63
    TypedDataSet
    -0.62
    readystatechange
    -0.61
     NgModule
    -0.60
    awaiter
    -0.59
     normaux
    -0.59
    POSITIVE LOGITS
    giving
    1.52
    Giving
    1.41
     Giving
    1.32
     giving
    1.14
    XmlAccessorType
    0.62
     welcoming
    0.57
     surla
    0.57
     saying
    0.56
     Giver
    0.54
    fsen
    0.54
    Activations Density 0.004%

    No Known Activations