© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 29780
    Prev
    Next
    INDEX
    Explanations

    prepositions relating one noun to another

    oai_token-act-pair · gemini-2.0-flash
    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
    +#+#
    -0.53
     lautet
    -0.51
     désolés
    -0.49
    škas
    -0.45
    doctype
    -0.44
    cop
    -0.44
     '{@
    -0.44
    gräns
    -0.44
     Cop
    -0.42
    httphttps
    -0.42
    POSITIVE LOGITS
    UnsafeEnabled
    0.66
     ContentValues
    0.65
     vVar
    0.63
     Shakspeare
    0.62
    ollectionView
    0.60
    daq
    0.59
    URBANA
    0.59
    ICTS
    0.59
    Unmarshaller
    0.59
    XtraEditors
    0.58
    Activations Density 0.358%

    No Known Activations