© 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. 38836
    Prev
    Next
    INDEX
    Explanations

    expressing doubt

    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
     myſelf
    -0.65
    évaluateur
    -0.62
    MockMvc
    -0.60
     surla
    -0.57
     ſeveral
    -0.56
    ospels
    -0.55
     Autorizaciones
    -0.53
     ſever
    -0.52
     становника
    -0.52
     Horus
    -0.52
    POSITIVE LOGITS
    +:+
    0.69
    istoitu
    0.61
     ourselves
    0.58
     yourselves
    0.58
     I
    0.57
    themselves
    0.54
     themselves
    0.51
     our
    0.50
     arşivlendi
    0.48
     merci
    0.48
    Activations Density 0.429%

    No Known Activations