© 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. 20-CLT-HP
    7. 75806
    Prev
    Next
    INDEX
    Explanations

    Preceding names

    np_max-act-logits · 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
     NTB
    -0.65
     Finns
    -0.63
    providedIn
    -0.59
    <bos>
    -0.58
     Mina
    -0.57
     PLA
    -0.57
     NIS
    -0.57
     flaps
    -0.56
     setuptools
    -0.56
    taman
    -0.56
    POSITIVE LOGITS
    -------------</
    0.40
     betweenstory
    0.39
    хран
    0.38
    ワイイ
    0.37
    qa
    0.37
     Wad
    0.37
     lilla
    0.36
     cromado
    0.35
    Qa
    0.34
     Hackett
    0.34
    Activations Density 0.000%

    No Known Activations