© 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. 92253
    Prev
    Next
    INDEX
    Explanations

    should

    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
     تضيفلها
    -0.78
    posedge
    -0.76
     extérieurs
    -0.69
     snippetHide
    -0.68
    Приятного
    -0.65
     extérieures
    -0.65
    berdayakan
    -0.65
    AxisAlignment
    -0.63
     defaultstate
    -0.61
     automatiques
    -0.61
    POSITIVE LOGITS
     also
    0.54
     stuff
    0.52
    rrggbb
    0.47
    PYX
    0.45
     considérons
    0.43
     stuffs
    0.42
     gawas
    0.41
     us
    0.41
     autorytatywna
    0.41
     “
    0.41
    Activations Density 0.000%

    No Known Activations