© 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. 5-CLT-HP
    7. 4698
    Prev
    Next
    INDEX
    Explanations

    0

    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
    Vidite
    -0.58
    rd
    -0.53
    lihood
    -0.52
    ➟
    -0.50
     мәкал
    -0.50
     Administrativna
    -0.50
     ***!
    -0.50
    XmlAccessorType
    -0.49
    webElementXpaths
    -0.49
    esez
    -0.46
    POSITIVE LOGITS
    rítica
    0.58
     endwhile
    0.56
    غيرة
    0.53
    Kelebihan
    0.52
    engertian
    0.52
     hidráulica
    0.52
    достатки
    0.51
    criptor
    0.51
     táctil
    0.51
     another
    0.51
    Activations Density 0.006%

    No Known Activations