© 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. 111
    Prev
    Next
    INDEX
    Explanations

    past tense verbs or adjectives that describe a state

    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
     tomorrow
    -0.89
     actuelles
    -0.88
    attuale
    -0.83
    antMatchers
    -0.82
     toekomst
    -0.79
     künftig
    -0.79
     prochaines
    -0.78
     amanhã
    -0.78
     actuels
    -0.78
    enumi
    -0.76
    POSITIVE LOGITS
     was
    1.30
     had
    1.16
     went
    1.09
    Twas
    1.08
     did
    1.05
     wasn
    1.05
     didn
    1.03
     came
    1.02
    twas
    0.99
     began
    0.97
    Activations Density 6.422%

    No Known Activations