© 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. 91858
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Datuak
    -0.60
     continúas
    -0.54
    zubauen
    -0.53
    escolar
    -0.53
     Normdatei
    -0.51
    graduates
    -0.51
     onOptions
    -0.50
    ścio
    -0.50
     vété
    -0.49
    Enllaces
    -0.49
    POSITIVE LOGITS
     a
    0.57
     the
    0.57
     where
    0.56
     and
    0.56
     but
    0.52
     reaching
    0.50
     crusher
    0.47
    writeObject
    0.47
    StoreMessageInfo
    0.47
     saturation
    0.47
    Activations Density 0.004%

    No Known Activations