© 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. 28519
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "that" in various contexts

    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
     beginnetje
    -0.89
    Jeografia
    -0.74
    CloseOperation
    -0.71
    RetentionPolicy
    -0.71
    ViewFeatures
    -0.69
    jspx
    -0.68
     ModelExpression
    -0.67
    Referanser
    -0.66
    Παραπομπές
    -0.64
    illoma
    -0.63
    POSITIVE LOGITS
     tslint
    0.59
     habet
    0.49
    <?
    0.48
    __))
    0.48
    Ports
    0.47
     bestäm
    0.47
    dow
    0.47
    dor
    0.47
     parach
    0.47
    piv
    0.46
    Activations Density 0.040%

    No Known Activations