© 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. 4-CLT-HP
    7. 1414
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     
    -0.49
     and
    -0.48
     like
    -0.47
     October
    -0.46
     German
    -0.46
     based
    -0.45
     other
    -0.45
     Russian
    -0.44
     including
    -0.43
     Indian
    -0.43
    POSITIVE LOGITS
     supérieurs
    0.76
    TagMode
    0.75
    Personensuche
    0.69
    رشف
    0.66
     nakalista
    0.65
    httphttps
    0.65
     démocr
    0.64
    <bos>
    0.64
    دانشنامهٔ
    0.63
     quelcon
    0.63
    Activations Density 0.038%

    No Known Activations