© 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. 14826
    Prev
    Next
    INDEX
    Explanations

    phrases that signal the beginning of discussions or arguments in a formal context

    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
    ]--;
    -0.86
    makeText
    -0.84
     uſed
    -0.82
     raiſ
    -0.81
     Efq
    -0.76
    ̈́
    -0.73
     ſeveral
    -0.72
    ModelSerializer
    -0.71
     tranſ
    -0.69
     Besar
    -0.68
    POSITIVE LOGITS
    enumi
    0.53
    featureID
    0.53
    qvarna
    0.52
    ymus
    0.52
    istoitu
    0.52
    gebnis
    0.51
     censiti
    0.49
     hasilnya
    0.49
    Tribune
    0.48
    Proceed
    0.47
    Activations Density 0.009%

    No Known Activations