© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17705
    Prev
    Next
    INDEX
    Explanations

    phrases related to network failure or 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
     tű
    -0.66
    an
    -0.60
    troppo
    -0.58
     demais
    -0.58
    ot
    -0.56
    ltä
    -0.56
     dă
    -0.55
     baix
    -0.55
     kväll
    -0.54
     aguda
    -0.54
    POSITIVE LOGITS
     estekak
    1.19
    writeFieldEnd
    1.02
    EndProject
    1.02
    bolista
    0.97
    WireFormatLite
    0.97
     propOrder
    0.97
    webElementGuid
    0.93
    ContentLoaded
    0.93
    IUrlHelper
    0.92
    DebuggerNonUser
    0.92
    Activations Density 0.012%

    No Known Activations