Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73454
    Prev
    Next
    INDEX
    Explanations

    Ory

    np_max-act-logits · 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
     Paglinawan
    -0.66
    Scénario
    -0.62
    EDEFAULT
    -0.57
     '\\;'
    -0.55
     agricole
    -0.51
     Formations
    -0.50
    Warm
    -0.50
    oneta
    -0.50
    standers
    -0.50
     Ferns
    -0.50
    POSITIVE LOGITS
     оригіналу
    0.53
     linkovi
    0.49
    Ming
    0.46
    IntoConstraints
    0.45
    ming
    0.44
     Ngb
    0.43
    Poli
    0.43
    InputBorder
    0.43
    lick
    0.43
    Clik
    0.43
    Activations Density 0.000%

    No Known Activations