© 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. 26033
    Prev
    Next
    INDEX
    Explanations

    terms related to prime numbers

    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
    :✨
    -0.53
    ernoo
    -0.47
    <eos>
    -0.47
    etsk
    -0.47
    side
    -0.45
     Pardo
    -0.45
    واعد
    -0.44
     Amérique
    -0.44
    addCriterion
    -0.44
     Signalez
    -0.44
    POSITIVE LOGITS
    libft
    0.75
    })$}
    0.70
    )":
    0.68
     StatefulWidget
    0.68
    Filmographie
    0.63
    paramref
    0.63
    rxjs
    0.63
    stdc
    0.63
    NoSuchAlgorithm
    0.63
    bkz
    0.62
    Activations Density 0.006%

    No Known Activations