© 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. 43452
    Prev
    Next
    INDEX
    Explanations

    roman numerals

    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
     XXIV
    -0.94
     XXVIII
    -0.86
     XXII
    -0.84
     XXVI
    -0.82
     XXI
    -0.80
     XIX
    -0.79
     XXV
    -0.78
     سكانية
    -0.77
     XXIX
    -0.76
     ddelweddau
    -0.76
    POSITIVE LOGITS
    <bos>
    0.59
    O
    0.58
    IP
    0.54
    A
    0.53
    Q
    0.53
    ON
    0.50
    I
    0.50
    U
    0.50
    OL
    0.49
    AT
    0.48
    Activations Density 0.621%

    No Known Activations