© 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. 24-RES-MATRYOSHKA-DC
    7. 751
    Prev
    Next
    INDEX
    Explanations

    verbs describing causation or allowance

    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.24.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.24.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
    they
    -0.55
    makeConstraints
    -0.54
     hennes
    -0.54
     ihres
    -0.54
     hendes
    -0.53
     they
    -0.52
    ArgsConstructor
    -0.51
     dessen
    -0.51
    PasswordEncoder
    -0.51
     Những
    -0.50
    POSITIVE LOGITS
     us
    3.33
     me
    1.80
     him
    1.66
     нам
    1.53
     you
    1.45
     нас
    1.41
     nosotros
    1.38
     them
    1.34
    เรา
    1.30
     нами
    1.30
    Activations Density 1.856%

    No Known Activations