© 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. 8428
    Prev
    Next
    INDEX
    Explanations

    dialogue or conversational exchanges, particularly phrases indicating uncertainty or disagreement

    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
    SPATH
    -0.65
    JspWriter
    -0.57
    visiae
    -0.55
    enterOuterAlt
    -0.55
     FetchType
    -0.54
    #![
    -0.54
     inderdaad
    -0.54
     Houſe
    -0.53
    proz
    -0.53
    ukseen
    -0.53
    POSITIVE LOGITS
    GeneratedValue
    0.51
    verwijspagina
    0.51
    Priv
    0.48
     VizieR
    0.45
     resourceCulture
    0.45
     برابوك
    0.44
    tagHelperRunner
    0.44
     privé
    0.43
    Div
    0.43
     Todes
    0.43
    Activations Density 0.026%

    No Known Activations