© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92256
    Prev
    Next
    INDEX
    Explanations

    mis, mus prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     touch
    -0.68
    edit
    -0.66
    ssos
    -0.58
    Transferred
    -0.56
     edit
    -0.51
    mis
    -0.50
    marginHorizontal
    -0.50
    mus
    -0.50
    Hochspringen
    -0.48
    nen
    -0.47
    POSITIVE LOGITS
     Biôgrafia
    0.69
    ymal
    0.68
    "]));
    0.63
    publicain
    0.61
     referrerpolicy
    0.59
    SharedDtor
    0.59
    ")));
    0.58
    Географиясе
    0.57
    ]!='
    0.56
     propOrder
    0.56
    Activations Density 0.130%

    No Known Activations