© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5994
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     au
    -0.43
     
    -0.35
     $
    -0.34
    ,
    -0.34
     (
    -0.33
     en
    -0.33
    ant
    -0.32
     O
    -0.31
     at
    -0.30
     five
    -0.30
    POSITIVE LOGITS
    ⓧ
    1.17
    ."));
    1.11
     Efq
    1.08
    ].)
    1.02
     propOrder
    1.02
    ^(@)
    1.01
    )";
    1.01
     Jefus
    1.01
    .")
    1.00
    .")]
    1.00
    Activations Density 0.011%

    No Known Activations