© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    formal language related to corporate communications and forward-looking statements

    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
    providedIn
    -0.65
    kiat
    -0.55
    Lähteet
    -0.54
     state
    -0.54
     statewide
    -0.52
    +:+
    -0.52
    OneToOne
    -0.52
     human
    -0.51
     stadig
    -0.51
    TintMode
    -0.50
    POSITIVE LOGITS
    Investor
    0.70
     shareholders
    0.69
     shareholder
    0.69
     investors
    0.67
     investor
    0.67
     Securities
    0.65
     Investor
    0.65
    investor
    0.64
     Investors
    0.63
     Shareholders
    0.62
    Activations Density 0.201%

    No Known Activations