© 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. 18472
    Prev
    Next
    INDEX
    Explanations

    details related to project management and communications in an organizational context

    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
     itſelf
    -1.19
     doubtnut
    -1.08
     houſe
    -1.05
     Theſe
    -1.05
     myſelf
    -1.05
     Shakspeare
    -1.04
     Efq
    -1.00
     diſt
    -0.99
    ChildScrollView
    -0.99
     ſche
    -0.99
    POSITIVE LOGITS
     A
    0.57
     We
    0.56
     I
    0.55
    <eos>
    0.54
     V
    0.52
     we
    0.52
     
    0.52
     #
    0.51
     D
    0.50
     a
    0.50
    Activations Density 0.152%

    No Known Activations