© 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. 20-CLT-HP
    7. 72688
    Prev
    Next
    INDEX
    Explanations

    uppercase letters

    np_max-act-logits · 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
     from
    -1.59
    from
    -1.04
     FROM
    -1.03
    จาก
    -0.92
     desde
    -0.86
     từ
    -0.86
     therefrom
    -0.84
     utafitiHapana
    -0.82
    FROM
    -0.81
     مرئيه
    -0.80
    POSITIVE LOGITS
     A
    0.57
    A
    0.53
    DebuggerNonUser
    0.40
     corner
    0.39
     comme
    0.38
     wall
    0.38
     lamp
    0.38
     stem
    0.38
     ogni
    0.38
    aarrggbb
    0.38
    Activations Density 0.000%

    No Known Activations