© 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. 4502
    Prev
    Next
    INDEX
    Explanations

    zo

    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
    Попис
    -0.59
    AnimationsModule
    -0.56
    #+#
    -0.49
    mybatisplus
    -0.43
    jonen
    -0.43
    šinou
    -0.41
     nakalista
    -0.41
    merksamkeit
    -0.41
     doInBackground
    -0.40
    jectures
    -0.40
    POSITIVE LOGITS
    ":"",
    0.57
     censiti
    0.57
    Rohy
    0.56
    BACA
    0.55
     advoc
    0.55
    ++
    0.54
    *}$
    0.54
     rhetor
    0.53
    exitRule
    0.53
    nasium
    0.52
    Activations Density 0.002%

    No Known Activations