© 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. 1-CLT-HP
    7. 10323
    Prev
    Next
    INDEX
    Explanations

    gment

    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
    gment
    -1.67
    gement
    -0.66
     sailboat
    -0.62
     Lub
    -0.58
    basicConfig
    -0.57
    Jeografia
    -0.55
     []:
    -0.55
    CodedInputStream
    -0.54
    DockStyle
    -0.53
    PhysRev
    -0.52
    POSITIVE LOGITS
     textStatus
    0.59
    expandindo
    0.59
     haki
    0.59
     tecnológica
    0.57
    ories
    0.57
     चीज़ों
    0.56
     affari
    0.56
     tecnológico
    0.54
     atmósfera
    0.53
     favoritos
    0.52
    Activations Density 0.086%

    No Known Activations