© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3573
    Prev
    Next
    INDEX
    Explanations

    Academic/technical texts

    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
    rophilic
    -0.51
    ELTS
    -0.47
     Hillsborough
    -0.43
     retra
    -0.42
    skyl
    -0.42
     seh
    -0.41
    magnetism
    -0.41
    ɚ
    -0.40
     hypot
    -0.40
     ECT
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.96
    WriteBarrier
    0.86
    AccessorTable
    0.81
    bootstrapcdn
    0.74
    Personendaten
    0.71
    ArrowToggle
    0.70
    AnchorStyles
    0.69
    PYX
    0.68
     AssemblyCulture
    0.68
     quelconque
    0.67
    Activations Density 0.012%

    No Known Activations