© 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. 3567
    Prev
    Next
    INDEX
    Explanations

    connection; expressing means

    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
    Портали
    -0.64
    ęku
    -0.63
    σιμο
    -0.62
     defaultstate
    -0.61
    VersionUID
    -0.59
    طلحات
    -0.59
    Portale
    -0.59
     AttributeSet
    -0.58
    niosek
    -0.58
    setVerticalGroup
    -0.58
    POSITIVE LOGITS
     at
    0.47
     in
    0.45
    muchas
    0.44
     most
    0.41
     abuela
    0.40
     gynhyrchwyd
    0.40
     duras
    0.39
     conventional
    0.39
    Handlung
    0.39
    IFICATION
    0.39
    Activations Density 0.002%

    No Known Activations