© 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. 17517
    Prev
    Next
    INDEX
    Explanations

    direct quotations and speech acts in the text

    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
    FTFY
    -0.70
    PhysRevD
    -0.68
     lenker
    -0.67
     CreateTagHelper
    -0.66
    MinWidth
    -0.66
    UnsafeEnabled
    -0.65
    rakech
    -0.62
     CanadaChoose
    -0.61
    typeorm
    -0.60
    ertale
    -0.60
    POSITIVE LOGITS
    CppMethod
    0.51
     CLIP
    0.50
     laikā
    0.47
    tagHelperRunner
    0.46
     Pues
    0.46
     découv
    0.45
    DebuggerNonUser
    0.45
     ComVisible
    0.43
    ReusableCell
    0.43
    ēju
    0.43
    Activations Density 0.003%

    No Known Activations