© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11352
    Prev
    Next
    INDEX
    Explanations

    alcohol

    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
    SourceChecksum
    -0.62
    Diweddarwch
    -0.59
    зулта
    -0.55
    chieben
    -0.55
    rzost
    -0.54
    нциклопедия
    -0.52
    CppMethod
    -0.52
    ี่ยน
    -0.52
     مشين
    -0.52
    المشاركات
    -0.52
    POSITIVE LOGITS
    AxisAlignment
    0.65
    protoimpl
    0.51
     MotionEvent
    0.50
    clientID
    0.50
    קישורים
    0.49
     setSelected
    0.49
     Courant
    0.47
    junge
    0.46
     Etr
    0.46
    AutoField
    0.46
    Activations Density 0.015%

    No Known Activations