© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43522
    Prev
    Next
    INDEX
    Explanations

    disorder

    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
     anarchy
    -1.33
     Theſe
    -1.32
     purpoſe
    -1.16
    +#+#
    -1.13
     myſelf
    -1.12
     Anſ
    -1.10
    VersionUID
    -1.09
     Efq
    -1.09
     greateſt
    -1.06
    ertia
    -1.05
    POSITIVE LOGITS
     of
    0.91
     in
    0.91
    .
    0.91
    ,
    0.88
     and
    0.81
    ;
    0.71
     (
    0.69
     at
    0.69
    :
    0.69
     on
    0.67
    Activations Density 0.061%

    No Known Activations