© 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. 4-CLT-HP
    7. 1001
    Prev
    Next
    INDEX
    Explanations

    only

    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
    SequentialGroup
    -0.66
    SBATCH
    -0.66
    dientemente
    -0.59
    AndEndTag
    -0.58
     للمعارف
    -0.56
     通販
    -0.55
     frequentemente
    -0.55
     gustaba
    -0.54
     disponíveis
    -0.54
     Autres
    -0.54
    POSITIVE LOGITS
     the
    0.91
     one
    0.81
     about
    0.74
     a
    0.69
     some
    0.66
     
    0.65
     small
    0.64
     an
    0.60
     certain
    0.59
     those
    0.57
    Activations Density 0.005%

    No Known Activations