© 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. 1-CLT-HP
    7. 15063
    Prev
    Next
    INDEX
    Explanations

    Pennsylvania, education, therapy

    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
     صوتيه
    -0.65
    AsUp
    -0.63
    <bos>
    -0.63
     Normdatei
    -0.62
     AssemblyCompany
    -0.60
     resourceCulture
    -0.60
    principalTable
    -0.59
    GIVEREF
    -0.58
    +#+#
    -0.57
    AndroidJUnit
    -0.57
    POSITIVE LOGITS
    ėk
    0.54
    ตร
    0.52
    saraba
    0.51
    getWriter
    0.48
    }/>
    0.47
    irt
    0.47
     $("<
    0.46
    წ
    0.46
     Explicit
    0.45
    haer
    0.45
    Activations Density 0.007%

    No Known Activations