© 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. 28345
    Prev
    Next
    INDEX
    Explanations

    terms related to signals and system errors

    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
    ztály
    -0.70
     kenn
    -0.67
     السود
    -0.63
     Ruk
    -0.63
     Turn
    -0.62
    <strong>
    -0.60
    Markup
    -0.60
     Brid
    -0.60
     slag
    -0.60
    entador
    -0.60
    POSITIVE LOGITS
     SIG
    1.48
    SIG
    1.21
     Sig
    1.00
     sig
    1.00
    Sig
    1.00
    sig
    0.96
    Personendaten
    0.94
    ToProps
    0.84
    MessageOf
    0.84
     Siga
    0.81
    Activations Density 0.006%

    No Known Activations