© 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. 92847
    Prev
    Next
    INDEX
    Explanations

    consistency

    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
    <bos>
    -1.19
    Diweddarwch
    -0.66
    Kariera
    -0.63
     Theſe
    -0.63
    SourceChecksum
    -0.60
    ὺ
    -0.58
     myſelf
    -0.58
    خصة
    -0.57
    єра
    -0.57
     propOrder
    -0.57
    POSITIVE LOGITS
    endphp
    0.47
    ="@+
    0.45
    BufferException
    0.44
    ViewFeatures
    0.42
    ThroughAttribute
    0.42
    MenuInflater
    0.41
    [...]
    0.39
     AssemblyProduct
    0.39
     simplicity
    0.38
    [*]
    0.38
    Activations Density 0.015%

    No Known Activations