© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 289
    Prev
    Next
    INDEX
    Explanations

    the word "release" or "released" often in the context of software and legal agreements.

    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
    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
    ActionMode
    -0.67
     AspNetCore
    -0.65
    rungsseite
    -0.65
     Wä
    -0.59
    fycat
    -0.58
    ometrial
    -0.56
    RegisterType
    -0.56
    PHONY
    -0.54
    raff
    -0.54
    ญิง
    -0.53
    POSITIVE LOGITS
     release
    2.81
     Release
    2.69
     released
    2.59
     releases
    2.56
    Release
    2.55
    release
    2.53
     RELEASE
    2.44
     releasing
    2.34
     Released
    2.34
     Releases
    2.33
    Activations Density 1.839%

    No Known Activations