© 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. 29493
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or hypothetical scenarios

    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
    Спољашње
    -0.81
    interopRequire
    -0.80
     AttributeSet
    -0.74
    談社
    -0.74
    Zac
    -0.73
    mstyle
    -0.73
    EReference
    -0.70
    ператор
    -0.67
    BagConstraints
    -0.66
    calaure
    -0.65
    POSITIVE LOGITS
     theaters
    0.83
     parlor
    0.80
    uesia
    0.73
    Theater
    0.72
    出版年
    0.68
    Hec
    0.67
    -------
    0.66
     sulfon
    0.65
     tires
    0.65
     sulfide
    0.65
    Activations Density 0.024%

    No Known Activations