© 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. 3-RES-MATRYOSHKA-DC
    7. 2372
    Prev
    Next
    INDEX
    Explanations

    objective C code

    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
     NSCoder
    -0.68
    ArgsConstructor
    -0.57
    rawDesc
    -0.57
    moveToNext
    -0.56
    GoogleApiClient
    -0.56
     kasarigan
    -0.56
    VersionUID
    -0.55
    XmlAccessType
    -0.52
    cupertino
    -0.52
    ]")]
    -0.52
    POSITIVE LOGITS
    ]--;
    0.57
    StartTag
    0.56
    DebuggerNonUser
    0.56
    ={`/
    0.55
    tissa
    0.54
    Tikang
    0.53
    ThroughAttribute
    0.53
    RTEE
    0.53
    quirrel
    0.52
    MessageWindow
    0.52
    Activations Density 0.105%

    No Known Activations