© 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. 91386
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ]")]
    -0.72
    InvalidProtocol
    -0.65
    +#+#
    -0.63
    RetentionPolicy
    -0.47
    ➟
    -0.46
    autique
    -0.45
     CreateTagHelper
    -0.44
    ^{*}=
    -0.44
    )))));
    -0.43
    specifier
    -0.42
    POSITIVE LOGITS
    liance
    0.53
    alike
    0.52
    ette
    0.52
    setColumns
    0.52
     Sylvain
    0.51
     Alumni
    0.50
    setColumn
    0.50
    setopt
    0.50
    PLACE
    0.50
    gler
    0.50
    Activations Density 0.016%

    No Known Activations