© 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. 22-RES-MATRYOSHKA-DC
    7. 1970
    Prev
    Next
    INDEX
    Explanations

    things that are blocking progress

    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
    ViewFeatures
    -0.56
    sidemargin
    -0.55
     calendriers
    -0.53
    localtime
    -0.51
     createSlice
    -0.50
     onOptions
    -0.50
     مُعرِّف
    -0.50
    uxxxx
    -0.48
    клопе
    -0.48
     carelessness
    -0.48
    POSITIVE LOGITS
     restricting
    1.82
     restrict
    1.78
     restriction
    1.78
     blocking
    1.71
     preventing
    1.68
     restricts
    1.68
     restrictions
    1.66
     prohibiting
    1.63
     inhibiting
    1.58
     prevent
    1.57
    Activations Density 3.635%

    No Known Activations