© 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. 22-RES-MATRYOSHKA-DC
    7. 2193
    Prev
    Next
    INDEX
    Explanations

    the word "am" and contractions of "I am"

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.66
     wireType
    -0.66
     GONNA
    -0.65
    enumi
    -0.60
    enumii
    -0.59
     chaude
    -0.53
     SqlDbType
    -0.53
    goog
    -0.52
     gonna
    -0.52
     pleins
    -0.52
    POSITIVE LOGITS
     Familienname
    0.65
    '}>
    0.59
     onResponse
    0.56
    Посилання
    0.50
    -};
    0.50
    rosserie
    0.48
     beginner
    0.48
    ukone
    0.47
     Developing
    0.46
    "}>
    0.46
    Activations Density 0.038%

    No Known Activations