© 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. 29507
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and relationships involving sequences and measures

    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
    [:]
    -0.60
    RegistryLite
    -0.58
    SharedCtor
    -0.58
    enderror
    -0.56
    #+#
    -0.55
    <thead>
    -0.54
     Mier
    -0.54
    ].)
    -0.54
    propTypes
    -0.53
    +#+
    -0.53
    POSITIVE LOGITS
     CreateTagHelper
    0.75
     uș
    0.70
     epä
    0.70
     îna
    0.65
     copertina
    0.63
     rând
    0.61
     ruok
    0.60
     kautta
    0.60
     mukana
    0.56
     tarko
    0.56
    Activations Density 0.031%

    No Known Activations