© 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. 5-CLT-HP
    7. 97533
    Prev
    Next
    INDEX
    Explanations

    di

    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
    <bos>
    -0.68
    зулта
    -0.63
     Brandt
    -0.52
    ptid
    -0.51
    ayak
    -0.50
    出版年
    -0.50
    gema
    -0.49
     Erickson
    -0.49
    ########.
    -0.49
    orge
    -0.48
    POSITIVE LOGITS
    principalColumn
    0.62
     MotionEvent
    0.61
    #+#
    0.55
    ivasan
    0.54
     Wicidata
    0.54
     Normdatei
    0.53
    stdc
    0.53
    MethodManager
    0.52
    IMPORTED
    0.52
    MemoryWarning
    0.50
    Activations Density 0.006%

    No Known Activations