© 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. 97771
    Prev
    Next
    INDEX
    Explanations

    studies and experiences

    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
     experiences
    -1.28
     EXPERI
    -0.98
    experiences
    -0.97
     experiencing
    -0.93
     Experiences
    -0.88
     experiencias
    -0.87
     esperienze
    -0.80
     expériences
    -0.74
     experimentar
    -0.68
     experiências
    -0.68
    POSITIVE LOGITS
    ToProps
    0.63
     שוליים
    0.57
    apore
    0.55
    anthes
    0.54
    idak
    0.53
     tanke
    0.53
    исленность
    0.53
    ills
    0.53
    odes
    0.53
     Serikat
    0.53
    Activations Density 0.143%

    No Known Activations