© 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. 2906
    Prev
    Next
    INDEX
    Explanations

    the word "was", some form of the verb "to be", and relative pronouns

    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
     itſelf
    -0.55
     ſte
    -0.52
    copically
    -0.51
    stuffs
    -0.50
    getMenuInflater
    -0.50
    waite
    -0.49
    alyptus
    -0.48
    ́t
    -0.48
    WebpackPlugin
    -0.48
     lloc
    -0.48
    POSITIVE LOGITS
     ones
    0.94
     Ones
    0.79
    Ones
    0.69
     theirs
    0.68
     others
    0.66
     Others
    0.66
    Others
    0.66
     quelli
    0.62
     them
    0.61
     antaranya
    0.60
    Activations Density 0.692%

    No Known Activations