© 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. 15140
    Prev
    Next
    INDEX
    Explanations

    sensor

    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
    IsMutable
    -0.57
     rê
    -0.54
     referenties
    -0.53
     AssemblyVersion
    -0.53
    <bos>
    -0.52
    pośred
    -0.52
    addPreferredGap
    -0.52
     Behind
    -0.52
    География
    -0.51
     manqué
    -0.51
    POSITIVE LOGITS
     plat
    0.56
    出版年
    0.55
     inflater
    0.53
    Plat
    0.53
    spect
    0.51
    oche
    0.51
     NSCoder
    0.50
    >--}}
    0.50
    bollah
    0.50
    flu
    0.48
    Activations Density 0.091%

    No Known Activations