© 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. 93515
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    AutoSize
    -0.53
    цездатний
    -0.46
     fédé
    -0.46
    Pub
    -0.45
    Naomi
    -0.45
     blz
    -0.44
    2
    -0.43
     tartalomajánló
    -0.43
    #+#
    -0.43
     privata
    -0.43
    POSITIVE LOGITS
    th
    0.63
    UTELY
    0.60
     useAppContext
    0.55
    ───
    0.54
     deposit
    0.53
    ungkinkan
    0.53
    帖最后由
    0.52
    camiseta
    0.52
     embe
    0.51
     Island
    0.51
    Activations Density 0.004%

    No Known Activations