© 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. 9747
    Prev
    Next
    INDEX
    Explanations

    terms related to the feasibility of studies or interventions

    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
     Mord
    -0.61
     mord
    -0.61
     Bundy
    -0.60
    mord
    -0.58
    Mord
    -0.58
    AGG
    -0.54
    qq
    -0.53
    elsen
    -0.53
     PUN
    -0.52
    SError
    -0.51
    POSITIVE LOGITS
    asibility
    1.32
     Feasibility
    1.27
     feasibility
    1.24
     feasible
    0.92
    asible
    0.92
    \{\\
    0.90
     feas
    0.88
     lenker
    0.84
    ⓘ
    0.84
     kasarigan
    0.78
    Activations Density 0.006%

    No Known Activations