© 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. 24-RES-MATRYOSHKA-DC
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    French language articles, prepositions, and possessive adjectives

    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.24.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.24.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
    âteau
    -0.70
    hastly
    -0.63
    ientôt
    -0.58
    liesslich
    -0.58
    órum
    -0.56
    auteuil
    -0.54
     laad
    -0.52
     maan
    -0.52
     countrymen
    -0.50
     matka
    -0.50
    POSITIVE LOGITS
    évaluateur
    0.52
    migrationBuilder
    0.45
    CloseOperation
    0.43
    hydrox
    0.43
     retten
    0.42
     utilizzati
    0.42
    ionine
    0.42
     quelcon
    0.42
     TextAppearance
    0.41
    ]=-
    0.41
    Activations Density 0.098%

    No Known Activations