© 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. 97019
    Prev
    Next
    INDEX
    Explanations

    Kab

    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
    DockStyle
    -1.17
    SequentialGroup
    -1.09
    Jeografia
    -1.07
    richTextPanel
    -1.06
     Савезне
    -1.05
    LookAnd
    -1.00
    OGND
    -0.98
     referenties
    -0.96
     <<<<<<<<<<<<<<
    -0.95
     lenker
    -0.90
    POSITIVE LOGITS
    :
    0.59
    <eos>
    0.48
    </blockquote>
    0.46
    —
    0.45
     :
    0.44
     —
    0.42
     esimerkiksi
    0.41
    """
    0.41
    E
    0.40
    ：
    0.40
    Activations Density 0.009%

    No Known Activations