© 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. 9702
    Prev
    Next
    INDEX
    Explanations

    negations and phrases that indicate uncertainty or lack of affirmation

    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
    amoan
    -0.64
     Вікі
    -0.62
    iciary
    -0.61
    rician
    -0.56
    amaran
    -0.56
    msgTypes
    -0.56
     Faso
    -0.55
    twimg
    -0.54
    |$.
    -0.53
    unhofer
    -0.52
    POSITIVE LOGITS
    ารถ
    0.59
     meta
    0.56
    meta
    0.52
    Meta
    0.51
     erk
    0.48
     campi
    0.48
    rensa
    0.47
    ivir
    0.46
     Meta
    0.45
    ądź
    0.45
    Activations Density 0.120%

    No Known Activations