© 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. 42281
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    RenderAtEndOf
    -1.27
     Efq
    -1.22
    تقاوى
    -1.16
     itſelf
    -1.14
    évaluateur
    -1.10
     ―――――
    -1.10
     myſelf
    -1.09
     Monfieur
    -1.08
     bezeichneter
    -1.05
    __':
    -1.03
    POSITIVE LOGITS
    '
    0.66
    ’
    0.62
    2
    0.60
     
    0.57
    The
    0.57
    <i>
    0.53
    ab
    0.52
    ;
    0.52
    ^
    0.51
    <b>
    0.51
    Activations Density 0.178%

    No Known Activations