© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3096
    Prev
    Next
    INDEX
    Explanations

    the adjective "sweet" in different contexts

    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
    EDEFAULT
    -0.79
    EndInit
    -0.63
    PMailer
    -0.60
     xxl
    -0.60
     Expl
    -0.60
     Lino
    -0.59
    fatti
    -0.59
    FailureListener
    -0.57
     خارجية
    -0.56
    cshtml
    -0.56
    POSITIVE LOGITS
     sweet
    3.42
    sweet
    3.25
     Sweet
    3.20
    Sweet
    3.19
     SWEET
    2.98
    SWEET
    2.91
     sweetest
    2.42
     sweetness
    2.39
     sweeter
    2.27
     süß
    2.05
    Activations Density 0.026%

    No Known Activations