© 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. 14691
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values or codes

    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
    лябин
    -0.58
    AddTagHelper
    -0.54
    مصادر
    -0.52
     kimia
    -0.51
    featureID
    -0.50
    TemporalType
    -0.49
    íncia
    -0.49
     récon
    -0.49
    ://$
    -0.49
     edif
    -0.49
    POSITIVE LOGITS
     []:
    0.63
    expandindo
    0.63
     Swedes
    0.56
     packers
    0.55
     ſeveral
    0.54
     gneiss
    0.53
    کز
    0.52
    SuppressLint
    0.51
    ientôt
    0.49
     corne
    0.49
    Activations Density 0.002%

    No Known Activations