© 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. 42713
    Prev
    Next
    INDEX
    Explanations

    salts and negative

    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
    aths
    -1.17
    uler
    -0.92
     salts
    -0.65
    ی
    -0.56
    at
    -0.50
     himo
    -0.50
    sv
    -0.50
     Salts
    -0.49
    sn
    -0.46
    sat
    -0.46
    POSITIVE LOGITS
    potranspiration
    0.60
    SPATH
    0.59
    cheiben
    0.58
    ])));
    0.58
     referenties
    0.55
    Graduated
    0.55
     snippetHide
    0.54
    IGraphics
    0.54
     viewDidLoad
    0.53
    acrylamide
    0.53
    Activations Density 1.857%

    No Known Activations