© 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. 5783
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
     WaitForSeconds
    -0.59
    DebuggerNonUser
    -0.57
    //
    -0.56
    jalá
    -0.56
    MLLoader
    -0.53
    новниш
    -0.52
     EINVAL
    -0.51
    wikkeld
    -0.50
    íritu
    -0.50
    quations
    -0.49
    POSITIVE LOGITS
    ????????
    0.93
    ??????
    0.91
     ?
    0.91
    ?”
    0.90
    ?
    0.89
    ?.
    0.88
    ?
    0.86
    ?"
    0.85
    ?—
    0.85
    ?}
    0.84
    Activations Density 0.061%

    No Known Activations