© 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. 4-CLT-HP
    7. 600
    Prev
    Next
    INDEX
    Explanations

    in

    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
    <bos>
    -0.49
    EditorBrowsable
    -0.47
    fjspx
    -0.46
    Newswire
    -0.44
     Obre
    -0.42
     fresas
    -0.41
    axiom
    -0.41
    kowski
    -0.40
    ">//
    -0.40
    ///</
    -0.40
    POSITIVE LOGITS
    TagMode
    0.81
    VIAF
    0.71
     autorytatywna
    0.69
     Favor
    0.66
    SPATH
    0.63
    SpringBootTest
    0.61
     VIAF
    0.61
     noDo
    0.60
     Himo
    0.60
    tagHelperRunner
    0.59
    Activations Density 0.000%

    No Known Activations