© 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. 0-CLT-HP
    7. 95137
    Prev
    Next
    INDEX
    Explanations

    location/position indicators

    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
     Below
    -0.92
    Below
    -0.92
    Before
    -0.87
     Before
    -0.86
    Behind
    -0.86
     Above
    -0.81
     Behind
    -0.81
    Prior
    -0.75
    tvguidetime
    -0.75
     Prior
    -0.73
    POSITIVE LOGITS
    ly
    0.78
     Enix
    0.75
    ConstraintMaker
    0.70
     You
    0.65
    most
    0.65
    teen
    0.64
    LY
    0.64
    hand
    0.63
     Us
    0.61
    ward
    0.60
    Activations Density 0.285%

    No Known Activations