© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 74
    Prev
    Next
    INDEX
    Explanations

    words expressing possibility, necessity, and intention

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    Personensuche
    -0.81
     Chriftian
    -0.76
     greateſt
    -0.70
     Diſ
    -0.69
     CURIAM
    -0.69
     forgets
    -0.67
    PreferredItem
    -0.67
    igshid
    -0.67
     Perſ
    -0.66
     lädt
    -0.66
    POSITIVE LOGITS
     be
    2.20
     have
    1.53
     become
    1.29
     come
    1.24
     remain
    1.16
     serve
    1.09
     appear
    1.08
     also
    1.08
     happen
    1.05
     provide
    1.04
    Activations Density 3.810%

    No Known Activations