© 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. 93938
    Prev
    Next
    INDEX
    Explanations

    code and license information

    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
    webElementXpaths
    -0.76
     ApiException
    -0.68
    ArrowToggle
    -0.65
     newOwner
    -0.59
    Jeografia
    -0.58
    NameInMap
    -0.55
    mybatisplus
    -0.54
     vendeurs
    -0.54
    abetes
    -0.53
    المشاركات
    -0.53
    POSITIVE LOGITS
    rungsseite
    0.52
    `,
    0.52
    ")),
    0.51
    stdc
    0.49
    AccessFile
    0.49
     Мексичка
    0.49
     referenties
    0.48
    httphttps
    0.47
    INCENT
    0.47
     uVar
    0.46
    Activations Density 1.564%

    No Known Activations