© 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. 6-RES-MATRYOSHKA-DC
    7. 305
    Prev
    Next
    INDEX
    Explanations

    references to a standard process or approach

    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
    DataMember
    -0.84
    Personensuche
    -0.84
    KommentareTeilen
    -0.83
    ="@+
    -0.66
    Geografi
    -0.64
    GEBURTSDATUM
    -0.62
    artifactId
    -0.59
     dön
    -0.59
    BrowserModule
    -0.58
    ouders
    -0.58
    POSITIVE LOGITS
     methods
    1.63
     ways
    1.57
     method
    1.48
    methods
    1.48
     Methods
    1.38
    Ways
    1.37
     techniques
    1.34
     Ways
    1.34
     Method
    1.30
     WAYS
    1.30
    Activations Density 2.530%

    No Known Activations