© 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. 4-CLT-HP
    7. 5056
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    readInt
    -0.49
    1
    -0.48
    oci
    -0.46
    5
    -0.45
    oc
    -0.44
     Do
    -0.43
    Do
    -0.43
    lic
    -0.43
    onia
    -0.41
    ou
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.75
    OGND
    0.73
    nosaurus
    0.67
     Audiodateien
    0.65
    setVerticalGroup
    0.65
     يتيمه
    0.64
    IsMutable
    0.63
    $__
    0.63
    SourceChecksum
    0.63
    \{\\
    0.61
    Activations Density 0.009%

    No Known Activations