© 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. 2-RES-MATRYOSHKA-DC
    7. 3960
    Prev
    Next
    INDEX
    Explanations

    references to attached files or documents

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.77
    ⓧ
    -0.66
     Deposition
    -0.65
     ContentValues
    -0.65
     deposition
    -0.63
     wall
    -0.62
    Personendaten
    -0.62
     Imm
    -0.60
    ResumeLayout
    -0.60
    commit
    -0.59
    POSITIVE LOGITS
     attached
    2.61
     Attached
    2.55
     attach
    2.42
    attached
    2.36
    Attached
    2.34
     attaches
    2.30
     attaching
    2.23
     attachment
    2.16
     Attach
    2.16
    attach
    2.11
    Activations Density 0.019%

    No Known Activations