© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94369
    Prev
    Next
    INDEX
    Explanations

    to

    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
    StandardCharsets
    -0.63
    umentos
    -0.53
    bootstrapcdn
    -0.52
    UnknownFieldSet
    -0.50
     liberate
    -0.49
    SOUNDBITE
    -0.49
     calibrate
    -0.48
     Nacionales
    -0.48
    CascadeType
    -0.46
    UNDLE
    -0.46
    POSITIVE LOGITS
    ContentAsync
    0.60
    SharedCtor
    0.59
    ")]
    0.59
     урна
    0.56
    "}";
    0.54
    setVerticalGroup
    0.54
    ).\
    0.54
    itra
    0.53
    ")]
    0.51
    TypedDataSet
    0.51
    Activations Density 0.007%

    No Known Activations