© 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. 951
    Prev
    Next
    INDEX
    Explanations

    Website content/archive

    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
    UnusedPrivate
    -0.47
     basso
    -0.46
     يتيمه
    -0.43
    BSA
    -0.39
    انگلیسی
    -0.39
    дея
    -0.37
     encomp
    -0.37
     memu
    -0.36
    ʺ
    -0.36
     flap
    -0.36
    POSITIVE LOGITS
     doInBackground
    0.84
    AxisAlignment
    0.73
    mybatisplus
    0.66
     مرئيه
    0.66
    tvguidetime
    0.65
     Viitattu
    0.63
    قایناقلار
    0.61
     defaultstate
    0.60
    hésite
    0.60
    DEPORTES
    0.60
    Activations Density 0.001%

    No Known Activations