© 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. 1182
    Prev
    Next
    INDEX
    Explanations

    the word "after."

    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
     follow
    -0.98
    follows
    -0.96
    complexContent
    -0.94
     Follows
    -0.93
     following
    -0.93
    follow
    -0.93
     follows
    -0.92
    following
    -0.91
     FOLLOW
    -0.89
    FOLLOW
    -0.87
    POSITIVE LOGITS
    bed
    0.68
    After
    0.66
     After
    0.66
     soffer
    0.66
    eker
    0.62
     fær
    0.62
     fter
    0.61
     Bez
    0.60
    ber
    0.59
    kosh
    0.59
    Activations Density 0.168%

    No Known Activations