© 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. 97668
    Prev
    Next
    INDEX
    Explanations

    recent

    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
     recent
    -2.25
    recent
    -1.99
     récente
    -1.81
    Recent
    -1.74
     RECENT
    -1.68
     Recent
    -1.67
     récentes
    -1.64
     récents
    -1.61
     reciente
    -1.59
     recente
    -1.55
    POSITIVE LOGITS
     powers
    0.59
    PRWEB
    0.53
     infringe
    0.52
     absur
    0.51
     vende
    0.51
     Modo
    0.51
     inferiority
    0.50
     arbitrage
    0.50
     incarnation
    0.50
    quelize
    0.49
    Activations Density 0.201%

    No Known Activations