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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45217
    Prev
    Next
    INDEX
    Explanations

    house

    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
     house
    -1.35
     House
    -1.20
    house
    -1.20
     HOUSE
    -1.13
    HOUSE
    -1.05
    House
    -1.02
    huis
    -0.88
    houses
    -0.84
     Houses
    -0.82
     houses
    -0.81
    POSITIVE LOGITS
    HasForeignKey
    0.60
    providedIn
    0.59
     sécher
    0.55
     vagues
    0.54
     termica
    0.53
     adaptées
    0.53
     refroid
    0.52
     naturelles
    0.51
     gouttes
    0.50
     gratuitas
    0.50
    Activations Density 0.054%

    No Known Activations