© 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. 12-RES-MATRYOSHKA-DC
    7. 26092
    Prev
    Next
    INDEX
    Explanations

    references to ordinal numbers, specifically focusing on "fifth" and "sixth."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    er
    -0.95
    ه
    -0.75
    ers
    -0.73
    es
    -0.71
    ة
    -0.66
     Bel
    -0.66
    eri
    -0.66
     Sec
    -0.64
    ing
    -0.64
     Ges
    -0.63
    POSITIVE LOGITS
     ISNI
    1.09
    theless
    0.92
     propOrder
    0.92
    anniversaire
    0.86
    multer
    0.84
    etheless
    0.83
     Theſe
    0.83
    Hentet
    0.82
    fifths
    0.82
    Normdaten
    0.81
    Activations Density 0.015%

    No Known Activations