© 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. 5-CLT-HP
    7. 91560
    Prev
    Next
    INDEX
    Explanations

    Stretching and flexibility

    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
    .*")]
    -0.69
    rungsseite
    -0.62
    ]--;
    -0.52
    äu
    -0.52
    LVANIA
    -0.52
    niel
    -0.51
    endphp
    -0.51
    IEL
    -0.49
     Hil
    -0.48
    auté
    -0.47
    POSITIVE LOGITS
    httphttps
    0.68
     rând
    0.60
    AddTagHelper
    0.59
     tightness
    0.55
     loos
    0.54
    enumii
    0.54
     Cárdenas
    0.52
    makeText
    0.49
    Tight
    0.49
     înainte
    0.49
    Activations Density 0.001%

    No Known Activations