© 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. 93990
    Prev
    Next
    INDEX
    Explanations

    RSV

    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
    RSV
    -0.63
     اكتوبر
    -0.60
    rtype
    -0.57
     désolés
    -0.54
    haped
    -0.54
    crypted
    -0.53
     يتيمه
    -0.52
    rador
    -0.52
    matous
    -0.52
    istic
    -0.51
    POSITIVE LOGITS
    =$?
    0.60
    __':
    0.60
     Савезне
    0.58
    ReusableCell
    0.58
    ⎨
    0.57
    Portale
    0.56
    setVerticalGroup
    0.56
     ویکی‌پدی
    0.56
    IndentedString
    0.56
     Mitarbeit
    0.55
    Activations Density 0.126%

    No Known Activations