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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94470
    Prev
    Next
    INDEX
    Explanations

    ose

    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
    ose
    -1.50
    OSE
    -0.95
     Story
    -0.89
    oses
    -0.85
     Stories
    -0.71
     STORY
    -0.66
    cose
    -0.62
    osing
    -0.60
     S
    -0.57
    Story
    -0.57
    POSITIVE LOGITS
     Majefty
    0.90
     Anſ
    0.87
    ſelf
    0.81
     ―――――
    0.81
     doubtnut
    0.76
     itſelf
    0.76
     greateſt
    0.76
     ſche
    0.74
     myſelf
    0.73
     DBNull
    0.71
    Activations Density 1.108%

    No Known Activations