© 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. 1-CLT-HP
    7. 10146
    Prev
    Next
    INDEX
    Explanations

    tree

    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
     EventArgs
    -0.49
     Perse
    -0.44
    })$}
    -0.44
    putra
    -0.43
     Aber
    -0.43
    RDP
    -0.42
     gmin
    -0.41
     Comprometido
    -0.41
     Akshay
    -0.40
    tahui
    -0.40
    POSITIVE LOGITS
    Autoritní
    0.76
    bootstrapcdn
    0.67
    mybatisplus
    0.66
    Revenir
    0.61
    帖最后由
    0.61
    ObjectContext
    0.60
    Manbalar
    0.60
    SourceChecksum
    0.59
    panou
    0.59
     CoreData
    0.59
    Activations Density 0.129%

    No Known Activations