© 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. 22653
    Prev
    Next
    INDEX
    Explanations

    statistical terms and related metrics

    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
     CreateTagHelper
    -1.04
     Viter
    -0.89
     שוליים
    -0.88
    eloma
    -0.86
     TDA
    -0.84
    ChildScrollView
    -0.83
    rungsseite
    -0.82
    ReusableCell
    -0.82
     Poche
    -0.79
     Castor
    -0.78
    POSITIVE LOGITS
    stat
    1.06
     stat
    1.02
     Stat
    0.96
     STAT
    0.90
    Stat
    0.82
    Statut
    0.77
    Stateless
    0.75
    STAT
    0.73
    Estat
    0.70
     Nat
    0.66
    Activations Density 0.022%

    No Known Activations